{"id":13737,"name":"open-webui/open-webui","ecosystem":"docker","repository_url":null,"issues_count":27,"created_at":"2025-06-06T23:33:21.925Z","updated_at":"2025-06-06T23:33:21.925Z","purl":"pkg:docker/open-webui/open-webui","unique_repositories_count":4,"unique_repositories_count_past_30_days":1,"recent_issues":[{"uuid":"4141310856","node_id":"PR_kwDOPIpjyc7Nm73m","number":36,"state":"closed","title":"Bump open-webui/open-webui from v0.8.8-slim to v0.8.11-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-03-27T07:16:24.000Z","author_association":null,"state_reason":null,"created_at":"2026-03-26T07:15:19.000Z","updated_at":"2026-03-27T07:16:26.000Z","time_to_close":86465,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.8.8-slim","new_version":"v0.8.11-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.8.8-slim to v0.8.11-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.11\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔀 \u003cstrong\u003eResponses API streaming improvements.\u003c/strong\u003e The OpenAI proxy now properly handles tool call streaming and re-invocations in the Responses API, preventing duplicate tool calls and preserving output during model re-invocations. \u003ca href=\"https://github.com/open-webui/open-webui/commit/93415a48e8893139db13d02d0a6d24e8604a2ac5\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f8b3a32caf00dad76687fd8fe698b86f304f3997\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/2ae47cf20057e92a83fd618b938f3ee9bb124e5b\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/adcbba34f8bbfbab3e4041269a084f2b71c076d9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔀 \u003cstrong\u003eResponses API stateful sessions.\u003c/strong\u003e Administrators can now enable experimental stateful session support via the ENABLE_RESPONSES_API_STATEFUL environment variable, allowing compatible backends to store responses server-side with previous_response_id anchoring for improved multi-turn conversations. \u003ca href=\"https://github.com/open-webui/open-webui/commit/dfc2dc2c0bd298cb4bfcf212ef11223586aa54f1\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eFile viewing pagination.\u003c/strong\u003e The view_file and view_knowledge_file tools now support pagination with offset and max_chars parameters, allowing models to read large files in chunks. \u003ca href=\"https://github.com/open-webui/open-webui/commit/5d7766e1b6f7ca7749c5a5a780d7b1bb2da28a2f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗺️ \u003cstrong\u003eKnowledge search scoping.\u003c/strong\u003e The search_knowledge_files tool now respects model-attached knowledge, searching only within attached knowledge bases and files when available. \u003ca href=\"https://github.com/open-webui/open-webui/commit/0f0ba7dadd043460d205477fd3b57556aa970847\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTool HTML embed context.\u003c/strong\u003e Tools can now return custom context alongside HTML embeds by using a tuple format, providing the LLM with actionable information instead of a generic message. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22691\"\u003e#22691\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eTrusted role header configuration.\u003c/strong\u003e Administrators can now configure the WEBUI_AUTH_TRUSTED_ROLE_HEADER environment variable to set user roles (admin, user, or pending) via a trusted header from their identity provider or reverse proxy. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22523\"\u003e#22523\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eOIDC authorization parameter injection.\u003c/strong\u003e Administrators can now inject extra parameters into the OIDC authorization redirect URL via the OAUTH_AUTHORIZE_PARAMS environment variable, enabling IdP pre-selection for brokers like CILogon and Keycloak. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22863\"\u003e#22863\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/69171a4c8bb7f995461b4a2feef194f112b32004\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eGoogle OAuth session persistence.\u003c/strong\u003e Administrators can now configure Google OAuth to issue refresh tokens via the GOOGLE_OAUTH_AUTHORIZE_PARAMS environment variable, preventing OAuth sessions from expiring after one hour and ensuring tools and integrations that rely on OAuth tokens remain functional. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22652\"\u003e#22652\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔌 \u003cstrong\u003eEmbed prompt confirmation.\u003c/strong\u003e Interactive tool embeds can now submit prompts to the chat without requiring same-origin access, showing a confirmation dialog for cross-origin requests to prevent abuse. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22908\"\u003e#22908\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏮 \u003cstrong\u003eTool binary response handling.\u003c/strong\u003e Tool servers can now return binary data such as images, which are properly processed and displayed in chat for both multimodal and non-multimodal models. \u003ca href=\"https://github.com/open-webui/open-webui/commit/1c25b06dca83ad491b4dc3d373b1c215a7a8fd3e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/108a019cb8e63a533250abe84f2b6f2b7c2131c4\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eSvelte upgrade performance.\u003c/strong\u003e Page and markdown rendering are now approximately 25% faster across the board, with significantly less memory usage for smoother UI interactions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22611\"\u003e#22611\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eModel and filter lookup optimization.\u003c/strong\u003e Model and filter membership lookups are now faster thanks to optimized data structure operations during model list loading. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7eae377c01f8d2de94a694b72279f769c82658cd\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eChat render throttling.\u003c/strong\u003e Chat message rendering now uses requestAnimationFrame batching to stay smooth during rapid model responses, preventing dropped frames when fast models send many events per second. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22947\"\u003e#22947\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eFunction list API optimization.\u003c/strong\u003e The functions list API now returns only essential metadata without function source code, reducing payload sizes by over 99% and making the Functions admin page load significantly faster. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22788\"\u003e#22788\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eSmoother loading animation.\u003c/strong\u003e The loading shimmer animation now looks smoother and more natural, with softer highlight colors. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22516\"\u003e#22516\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧪 \u003cstrong\u003eTerminal connection verification.\u003c/strong\u003e Users can now verify their terminal server connection is working before saving the configuration, making setup more reliable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22567\"\u003e#22567\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eChat folder emoji reset.\u003c/strong\u003e Users can now reset chat folder emojis back to the default icon using a \u0026quot;Reset to Default\u0026quot; button in the emoji picker, making it easier to revert custom icons. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22554\"\u003e#22554\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eMetrics export interval configuration.\u003c/strong\u003e Administrators can now control OpenTelemetry metrics export frequency via the OTEL_METRICS_EXPORT_INTERVAL_MILLIS environment variable, enabling cost optimization for metrics services like Grafana Cloud. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22529\"\u003e#22529\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏥 \u003cstrong\u003eReadiness probe endpoint.\u003c/strong\u003e A new /ready endpoint is now available for Kubernetes deployments, returning 200 only after startup completes and database/Redis are reachable, enabling more reliable container orchestration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22507\"\u003e#22507\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔩 \u003cstrong\u003eTool server timeout configuration.\u003c/strong\u003e Administrators can now configure a separate HTTP timeout for tool server requests via the AIOHTTP_CLIENT_TIMEOUT_TOOL_SERVER environment variable, enabling fine-tuned control over how long tool calls are allowed to take. \u003ca href=\"https://github.com/open-webui/open-webui/commit/a3238aa79f344765f5b62cb64eba71ffd001abaf\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eKnowledge file previews.\u003c/strong\u003e Knowledge base files can now be opened in a new tab directly from the file list, making it easier to view content without downloading. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22629\"\u003e#22629\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eKnowledge tool hybrid search support.\u003c/strong\u003e The built-in query_knowledge_files tool now respects hybrid search and reranking settings, matching the behavior of the middleware RAG pipeline. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a2c60d5954ecbc172d09e9955d52a07d135dcbc\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eTemporary chat folder support.\u003c/strong\u003e Temporary chats can now use folder-level system prompts and knowledge files, making them more powerful for quick explorations. \u003ca href=\"https://github.com/open-webui/open-webui/commit/adcc50d3370301afd5561e0f58ff6f3ab3750818\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📡 \u003cstrong\u003eTerminal port previews.\u003c/strong\u003e Detected ports in the File Navigator can now be previewed inline with a browser-style view, navigation controls, and an address bar, instead of only opening in a new tab. \u003ca href=\"https://github.com/open-webui/open-webui/commit/689061822173e561a153290b2bb816f4cb6f4959\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/1dc647f43b1929f5c4d1af393a90a47f56cb745e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eFile renaming.\u003c/strong\u003e Files and folders in the File Navigator can now be renamed by double-clicking or using the context menu, with Enter to confirm and Escape to cancel. \u003ca href=\"https://github.com/open-webui/open-webui/commit/637cd136c2271baf4787815bc8bc25241626a943\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧭 \u003cstrong\u003eFile Navigator navigation history.\u003c/strong\u003e The File Navigator toolbar now includes Back and Forward buttons for navigating through folder and file history, similar to a web browser. \u003ca href=\"https://github.com/open-webui/open-webui/commit/3a4b862e818c69fff6f3a3c67b50c51aa00c03e9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eDelete connection confirmations.\u003c/strong\u003e Users are now prompted with a confirmation dialog before deleting connections, preventing accidental deletions. \u003ca href=\"https://github.com/open-webui/open-webui/commit/157ff57c40bc40c53bc608828dac3779e95c2ffa\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eDocument loader fallbacks.\u003c/strong\u003e Excel and PowerPoint files can now be processed even when the unstructured package is not installed, using pandas and python-pptx as fallback loaders. \u003ca href=\"https://github.com/open-webui/open-webui/commit/6862d618ee17f95d3cae78819ed993e7fbc7e632\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eMemory management search and sort.\u003c/strong\u003e Users can now search and sort their personal memories in the Memory management modal, making it easier to find specific memories. \u003ca href=\"https://github.com/open-webui/open-webui/commit/47ab4c71d50fd631b04c95f2febb085dd0a13083\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eSBOM generation script.\u003c/strong\u003e A new script for generating CycloneDX Software Bill of Materials is now available in the scripts directory. \u003ca href=\"https://github.com/open-webui/open-webui/commit/39100eca4915e4fe86a6912aa97dde86ed72e015\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eRuff linter and formatter.\u003c/strong\u003e Added Ruff as the Python linter and formatter, replacing the black-based workflow for better code quality with near-instant execution. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22576\"\u003e#22576\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/22462\"\u003e#22462\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eOffline code formatting support.\u003c/strong\u003e The black formatter for Python code editing is now bundled locally in the Docker image, enabling code formatting to work in air-gapped deployments where client browsers cannot reach PyPI. Formatting failures no longer block saves, allowing code to be preserved even when offline. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22509\"\u003e#22509\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8507e5eb0d18896f1bbf990a00a4361aec171a30\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eMarkdown file editing.\u003c/strong\u003e Users can now edit and save Markdown files directly in the file navigator, with empty files automatically switching to editor mode for immediate editing. \u003ca href=\"https://github.com/open-webui/open-webui/commit/47e47e42af682e7f75c8359999f7cdf969bf903e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🍔 \u003cstrong\u003eModel bulk actions menu.\u003c/strong\u003e Users can now quickly enable, disable, show, or hide multiple models at once using a new hamburger menu on the workspace Models page filter bar, with actions respecting the current search and filter settings. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22484\"\u003e#22484\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eFiles list pagination.\u003c/strong\u003e The files list API now supports pagination, returning paginated results with a total count for easier navigation through large file collections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f9756de693a93e918c037d757afddb7defc847e4\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖇 \u003cstrong\u003eWeb fetch content length config.\u003c/strong\u003e Administrators can now configure the maximum characters to return from fetched URLs via WEB_FETCH_MAX_CONTENT_LENGTH environment variable or the admin settings page, instead of the previous hardcoded 50K limit. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b171b0216b916745420c7caf513093a315ed9560\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22774\"\u003e#22774\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eOllama Anthropic endpoint support.\u003c/strong\u003e The Ollama proxy now supports the Anthropic-compatible /v1/messages endpoint, allowing clients using the Anthropic API format to work through Open WebUI with proper authentication and model access controls. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f23296b22d3304e5bfcd19151e5802eec55bd98f\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22861\"\u003e#22861\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eWriting block rendering.\u003c/strong\u003e Responses from OpenAI models that include :::writing blocks are now rendered as formatted content in a styled container with a copy button, instead of displaying raw marker text. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22672\"\u003e#22672\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/53b8a1f71bd0cb0a0122175ad5210da492018728\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eMemory deletion confirmation.\u003c/strong\u003e Users are now asked to confirm before deleting individual memory entries, with the memory content displayed for review. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22888\"\u003e#22888\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📓 \u003cstrong\u003eMulti-artifact HTML rendering.\u003c/strong\u003e Code blocks with multiple HTML sections now render as separate artifacts instead of merging into one, allowing models to display distinct interactive components. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a6bf78e14a13864e72db87426da4f5996abe716\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚩 \u003cstrong\u003eDrag chats as references.\u003c/strong\u003e Users can now drag chats from the sidebar and drop them into the message input to add them as Reference Chats. \u003ca href=\"https://github.com/open-webui/open-webui/commit/ebb7ce2092efc8d78da4974623647dbd18b6e372\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eTerminal system prompts.\u003c/strong\u003e Terminal servers can now provide custom system prompts that are automatically included when their tools are used. \u003ca href=\"https://github.com/open-webui/open-webui/commit/6a9d67b5bb4c93fd343b334bee3e37703dff59f6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eTerminal state persistence.\u003c/strong\u003e The selected terminal server and its enabled state now persist across page loads, making terminal usage more seamless. \u003ca href=\"https://github.com/open-webui/open-webui/commit/d577ff1e4af750dda09e558dac7edb8dd2470850\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eTerminal folder downloads.\u003c/strong\u003e Users can now download folders as ZIP archives and bulk-download multiple selected files as a single ZIP directly from the File Navigator toolbar, making file exports faster and more convenient. \u003ca href=\"https://github.com/open-webui/open-webui/commit/3841e85abb3ea3e8d8b364dff0102f0124844d22\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/cf60b1882f1929200649b59f867289dea54e4210\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eMCP OAuth 2.1 static credentials.\u003c/strong\u003e MCP servers that require static client_id and client_secret can now be connected using a new OAuth 2.1 Static auth type, enabling integration with MCP servers that don't support dynamic client registration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22266\"\u003e#22266\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/601bb783587a3e965cf88c148e4856b988655b13\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎪 \u003cstrong\u003eCollapsible tool and thinking groups.\u003c/strong\u003e Consecutive tool calls and reasoning blocks are now grouped into a single collapsible summary (e.g., \u0026quot;Explored tool1, tool2\u0026quot;), keeping chat responses clean and readable while preserving full detail on expand. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21604\"\u003e#21604\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/261aec8c864646eb7215be0d5c14a79cad3cb93f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eGeneral improvements.\u003c/strong\u003e Various improvements were implemented across the application to enhance performance, stability, and security.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4d058a125b17eb57212af5eab98d683548d546e3\"\u003e\u003ccode\u003e4d058a1\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/23035\"\u003e#23035\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f12252531066762c85d8e180143bfc74260eacc9\"\u003e\u003ccode\u003ef122525\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f5f128620a404396bd56895d0e039f3c79f905be\"\u003e\u003ccode\u003ef5f1286\u003c/code\u003e\u003c/a\u003e chore: ci\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/06635898d0960235d0bb1931f595c772e2e3652b\"\u003e\u003ccode\u003e0663589\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0ded0b706919896e79bb43f3733f84d22889302d\"\u003e\u003ccode\u003e0ded0b7\u003c/code\u003e\u003c/a\u003e chore: ci\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0fa246a1c3ad3aa85945fac487494b5bd69603ad\"\u003e\u003ccode\u003e0fa246a\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8cb47aebae5e924fcd936741649d97cf0680032f\"\u003e\u003ccode\u003e8cb47ae\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/bfc606a9e3065065bd9bfe4e1e9206236a94e987\"\u003e\u003ccode\u003ebfc606a\u003c/code\u003e\u003c/a\u003e fix: align file context injection by user-role messages for native FC (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22776\"\u003e#22776\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7a21933d100733963fb54ebdd208825d1f5b8411\"\u003e\u003ccode\u003e7a21933\u003c/code\u003e\u003c/a\u003e chore: changelog (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22569\"\u003e#22569\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9364e2fb74a0a69b2618a761526165b63d4815ff\"\u003e\u003ccode\u003e9364e2f\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.8.8...v0.8.11\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.8.8-slim\u0026new-version=v0.8.11-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/36","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/36","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/36/packages"},{"uuid":"3982029016","node_id":"PR_kwDOPvrhr87F2Epp","number":46,"state":"closed","title":"Bump open-webui/open-webui from 0.6.43 to 0.8.5 in /charts/open-webui","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-03-01T07:09:02.000Z","author_association":null,"state_reason":null,"created_at":"2026-02-24T07:28:24.000Z","updated_at":"2026-03-01T07:09:03.000Z","time_to_close":430838,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.43","new_version":"0.8.5","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/charts/open-webui","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.43 to 0.8.5.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.5\u003c/h2\u003e\n\u003ch2\u003e[0.8.5] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eVoice dictation shortcut.\u003c/strong\u003e Users can now toggle voice dictation using Cmd+Shift+L (or Ctrl+Shift+L on Windows/Linux), making it faster to start and stop dictation without clicking the microphone button.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eModel access KeyError fix.\u003c/strong\u003e The /api/models endpoint no longer crashes with a 500 error when models have incomplete info metadata missing the user_id field (e.g. models using global default metadata).\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eFrontend initialization resilience.\u003c/strong\u003e The app layout now gracefully handles individual API failures during initialization (getModels, getBanners, getTools, getUserSettings, setToolServers) instead of blocking the entire page load when any single call fails.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eBackend config null safety.\u003c/strong\u003e Language detection during app initialization no longer crashes when the backend config fetch fails, preventing a secondary cause of infinite loading.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.4\u003c/h2\u003e\n\u003ch2\u003e[0.8.4] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛜 \u003cstrong\u003eProvider URL suggestions.\u003c/strong\u003e The connection form now displays a dropdown with suggested URLs for popular AI providers, making it easier to configure connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/49c36238d01aaff5466344ecd316a6dd3edd74a3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ \u003cstrong\u003eAnthropic model fetching.\u003c/strong\u003e The system now properly fetches available models from the Anthropic API, ensuring all Anthropic models are accessible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e9d852545cc17f0eeb8bdcfa77575a80fed8706d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eNo models prompt.\u003c/strong\u003e When no models are available, a helpful prompt now guides users to manage their provider connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/a0195cd5ae9b9915295839cd0a5fbac5a1b0bfa2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConnection enable/disable toggles.\u003c/strong\u003e Individual provider connections can now be enabled or disabled from both admin and user settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/990c638f6cf91507b61898f454c26f9516114c36\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⏸️ \u003cstrong\u003ePrompt enable/disable toggle.\u003c/strong\u003e Users can now enable or disable prompts directly from the prompts list using a toggle switch, without needing to delete and recreate them. Inactive prompts display an \u0026quot;Inactive\u0026quot; badge and are still visible in the list. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eMemory deletion.\u003c/strong\u003e Agents can now delete specific memories that are no longer relevant, duplicated, or incorrect, giving better control over stored memory content. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eMemory listing.\u003c/strong\u003e Agents can now list all stored memories, enabling them to identify which memories to manage or delete based on the complete memory inventory. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eAuto pip install toggle.\u003c/strong\u003e Administrators can now disable automatic pip package installation from function frontmatter requirements using the ENABLE_PIP_INSTALL_FRONTMATTER_REQUIREMENTS environment variable, providing more control over function dependency management. \u003ca href=\"https://github.com/open-webui/open-webui/commit/8bfab327ec5f635f9fe93c26efd198712ff7116d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eAnthropic Messages API proxy.\u003c/strong\u003e A new API endpoint now supports the Anthropic Messages API format, allowing tools like Claude Code to authenticate through Open WebUI and access configured models. Tool calls are now properly supported in streaming responses with correct multi-block indexing, and error status from tools is propagated correctly. The endpoint converts requests to OpenAI format internally, routes them through the existing chat pipeline, and returns responses in Anthropic format. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21390\"\u003e#21390\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/91a0301c9e22e93295a7c471d83592a802560795\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a9312d25373d3aa161788598f87180b8db11c5b6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eMulti-device OAuth sessions.\u003c/strong\u003e Users can now stay logged in on multiple devices simultaneously with OAuth, as re-logging in no longer terminates existing sessions. The oldest sessions are automatically pruned when the session limit is exceeded. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21647\"\u003e#21647\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/ae05586fdabf318d551b53ede41575355d3b9e2b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth group default share setting.\u003c/strong\u003e Administrators can now configure the default sharing setting for OAuth-created groups using the OAUTH_GROUP_DEFAULT_SHARE environment variable, allowing control over whether new groups default to private or shared with members. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21679\"\u003e#21679\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4b9f821b58007d4efa4aa16a4995b23126e08a88\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eKnowledge base import behavior.\u003c/strong\u003e The web content import endpoint now supports a configurable overwrite flag, allowing users to add multiple URLs to the same knowledge base instead of replacing existing content. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21613\"\u003e#21613\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21336\"\u003e#21336\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4bef69cc6344ff809090441aa6bced573a2aa838\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSkill JSON import support.\u003c/strong\u003e Skills can now be imported from both JSON and Markdown files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21511\"\u003e#21511\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eYou.com web search provider.\u003c/strong\u003e A new web search provider option for You.com is now available, giving users another search engine choice for web-enabled models. The You.com provider enriches search results by including both descriptions and snippets for better context. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21599\"\u003e#21599\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eMessage list performance.\u003c/strong\u003e Loading conversation history when sending messages is now significantly faster, improving response latency before the model starts generating. This also speeds up chat search and RAG context building. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21588\"\u003e#21588\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eConcurrent embedding request control.\u003c/strong\u003e Administrators can now control the maximum number of concurrent embedding API requests using the RAG_EMBEDDING_CONCURRENT_REQUESTS environment variable, helping manage API rate limits while maintaining embedding performance. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21662\"\u003e#21662\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/5d4547f934b6fbe751bb2041f9597fe11ddf8e43\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage upsert optimization.\u003c/strong\u003e Loading chat data during message saving is now significantly faster by eliminating a redundant database call that occurred on every message upsert, which happens many times during streaming responses. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21592\"\u003e#21592\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage send optimization.\u003c/strong\u003e Loading chat data during message sending is now significantly faster by eliminating unnecessary full conversation history loads. The system now uses targeted queries that fetch only the needed data instead of loading entire chat objects with all message history. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21596\"\u003e#21596\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eTag filtering optimization.\u003c/strong\u003e Chat search with tag filtering now uses more efficient database queries, making filtered searches significantly faster. \u003ca href=\"https://github.com/open-webui/open-webui/commit/139f02a9d9fa2ffffcc96aa0de8af8ef51b6bcf2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eShared chat loading optimization.\u003c/strong\u003e The shared chats endpoint now loads only the needed columns instead of the full conversation history, making shared chat listings significantly faster. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21614\"\u003e#21614\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eArchived and pinned chat loading.\u003c/strong\u003e Loading archived and pinned chat lists is now significantly faster by loading only the needed columns instead of full conversation data. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21591\"\u003e#21591\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eChat title query optimization.\u003c/strong\u003e Retrieving chat titles now queries only the title column instead of the entire conversation history, making title lookups significantly faster and reducing database load. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21590\"\u003e#21590\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eBatch access grants for multiple resources.\u003c/strong\u003e Loading channels, knowledge bases, models, notes, prompts, skills, and tools now uses batch database queries for access grants instead of individual queries per item, significantly reducing database load. For 30 items, this reduces approximately 31 queries to just 3. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21616\"\u003e#21616\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eNotes list payload optimization.\u003c/strong\u003e Notes list and search endpoints now return only a 200-character preview instead of the full note content, reducing response payload from ~167 MB to ~10 KB for 60 notes and eliminating N+1 queries for access grants. The Notes tab now loads in seconds instead of tens of seconds. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21549\"\u003e#21549\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eTools list performance.\u003c/strong\u003e Loading the tools list is now significantly faster by deferring content and specs fields from database queries, and using cached tool modules instead of reloading them for each request. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b48594a16680cc77921a4ed1a11ffa07df7edc60\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eGroup description display.\u003c/strong\u003e The admin groups list now shows each group's description, making it easier for administrators to identify groups at a glance.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eSort by dropdown.\u003c/strong\u003e Administrators can now sort groups using a dropdown menu with options for Name or Members, replacing the previous clickable column headers.\u003c/li\u003e\n\u003cli\u003e📶 \u003cstrong\u003eAdmin groups list sorting.\u003c/strong\u003e The Group and Users columns in the admin groups list are now clickable for sorting, allowing administrators to sort groups alphabetically by name or numerically by member count. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21692\"\u003e#21692\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔽 \u003cstrong\u003eRich UI auto-scroll.\u003c/strong\u003e The view now automatically scrolls to action-generated Rich UI content once it renders, ensuring users can see the results without manually scrolling. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21698\"\u003e#21698\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21482\"\u003e#21482\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAdmin analytics toggle.\u003c/strong\u003e Administrators can now enable or disable the analytics feature using the ENABLE_ADMIN_ANALYTICS environment variable, giving more control over available admin features. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21651\"\u003e#21651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/35598b8017557258b8c9ee3469d320adb0140751\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAnalytics sorting enhancement.\u003c/strong\u003e The Analytics dashboard now supports sorting by Tokens column for both Model Usage and User Usage tables, and the Share/Percentage columns are now clickable for sorting. Administrators can more easily identify the most token-consuming models and users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/053a33631f575ae1ad3123190a9e820b4057f62d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📑 \u003cstrong\u003eFetch URL citation sources.\u003c/strong\u003e When models fetch URLs during tool calling, the fetched URLs now appear as clickable citation sources in the UI with content previews, matching the existing behavior of web search and knowledge file tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21669\"\u003e#21669\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.8.5] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eVoice dictation shortcut.\u003c/strong\u003e Users can now toggle voice dictation using Cmd+Shift+L (or Ctrl+Shift+L on Windows/Linux), making it faster to start and stop dictation without clicking the microphone button.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eModel access KeyError fix.\u003c/strong\u003e The /api/models endpoint no longer crashes with a 500 error when models have incomplete info metadata missing the user_id field (e.g. models using global default metadata).\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eFrontend initialization resilience.\u003c/strong\u003e The app layout now gracefully handles individual API failures during initialization (getModels, getBanners, getTools, getUserSettings, setToolServers) instead of blocking the entire page load when any single call fails.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eBackend config null safety.\u003c/strong\u003e Language detection during app initialization no longer crashes when the backend config fetch fails, preventing a secondary cause of infinite loading.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.8.4] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛜 \u003cstrong\u003eProvider URL suggestions.\u003c/strong\u003e The connection form now displays a dropdown with suggested URLs for popular AI providers, making it easier to configure connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/49c36238d01aaff5466344ecd316a6dd3edd74a3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ \u003cstrong\u003eAnthropic model fetching.\u003c/strong\u003e The system now properly fetches available models from the Anthropic API, ensuring all Anthropic models are accessible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e9d852545cc17f0eeb8bdcfa77575a80fed8706d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eNo models prompt.\u003c/strong\u003e When no models are available, a helpful prompt now guides users to manage their provider connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/a0195cd5ae9b9915295839cd0a5fbac5a1b0bfa2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConnection enable/disable toggles.\u003c/strong\u003e Individual provider connections can now be enabled or disabled from both admin and user settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/990c638f6cf91507b61898f454c26f9516114c36\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⏸️ \u003cstrong\u003ePrompt enable/disable toggle.\u003c/strong\u003e Users can now enable or disable prompts directly from the prompts list using a toggle switch, without needing to delete and recreate them. Inactive prompts display an \u0026quot;Inactive\u0026quot; badge and are still visible in the list. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eMemory deletion.\u003c/strong\u003e Agents can now delete specific memories that are no longer relevant, duplicated, or incorrect, giving better control over stored memory content. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eMemory listing.\u003c/strong\u003e Agents can now list all stored memories, enabling them to identify which memories to manage or delete based on the complete memory inventory. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eAuto pip install toggle.\u003c/strong\u003e Administrators can now disable automatic pip package installation from function frontmatter requirements using the ENABLE_PIP_INSTALL_FRONTMATTER_REQUIREMENTS environment variable, providing more control over function dependency management. \u003ca href=\"https://github.com/open-webui/open-webui/commit/8bfab327ec5f635f9fe93c26efd198712ff7116d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eAnthropic Messages API proxy.\u003c/strong\u003e A new API endpoint now supports the Anthropic Messages API format, allowing tools like Claude Code to authenticate through Open WebUI and access configured models. Tool calls are now properly supported in streaming responses with correct multi-block indexing, and error status from tools is propagated correctly. The endpoint converts requests to OpenAI format internally, routes them through the existing chat pipeline, and returns responses in Anthropic format. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21390\"\u003e#21390\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/91a0301c9e22e93295a7c471d83592a802560795\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a9312d25373d3aa161788598f87180b8db11c5b6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eMulti-device OAuth sessions.\u003c/strong\u003e Users can now stay logged in on multiple devices simultaneously with OAuth, as re-logging in no longer terminates existing sessions. The oldest sessions are automatically pruned when the session limit is exceeded. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21647\"\u003e#21647\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/ae05586fdabf318d551b53ede41575355d3b9e2b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth group default share setting.\u003c/strong\u003e Administrators can now configure the default sharing setting for OAuth-created groups using the OAUTH_GROUP_DEFAULT_SHARE environment variable, allowing control over whether new groups default to private or shared with members. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21679\"\u003e#21679\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4b9f821b58007d4efa4aa16a4995b23126e08a88\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eKnowledge base import behavior.\u003c/strong\u003e The web content import endpoint now supports a configurable overwrite flag, allowing users to add multiple URLs to the same knowledge base instead of replacing existing content. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21613\"\u003e#21613\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21336\"\u003e#21336\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4bef69cc6344ff809090441aa6bced573a2aa838\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSkill JSON import support.\u003c/strong\u003e Skills can now be imported from both JSON and Markdown files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21511\"\u003e#21511\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eYou.com web search provider.\u003c/strong\u003e A new web search provider option for You.com is now available, giving users another search engine choice for web-enabled models. The You.com provider enriches search results by including both descriptions and snippets for better context. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21599\"\u003e#21599\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eMessage list performance.\u003c/strong\u003e Loading conversation history when sending messages is now significantly faster, improving response latency before the model starts generating. This also speeds up chat search and RAG context building. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21588\"\u003e#21588\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eConcurrent embedding request control.\u003c/strong\u003e Administrators can now control the maximum number of concurrent embedding API requests using the RAG_EMBEDDING_CONCURRENT_REQUESTS environment variable, helping manage API rate limits while maintaining embedding performance. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21662\"\u003e#21662\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/5d4547f934b6fbe751bb2041f9597fe11ddf8e43\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage upsert optimization.\u003c/strong\u003e Loading chat data during message saving is now significantly faster by eliminating a redundant database call that occurred on every message upsert, which happens many times during streaming responses. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21592\"\u003e#21592\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage send optimization.\u003c/strong\u003e Loading chat data during message sending is now significantly faster by eliminating unnecessary full conversation history loads. The system now uses targeted queries that fetch only the needed data instead of loading entire chat objects with all message history. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21596\"\u003e#21596\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eTag filtering optimization.\u003c/strong\u003e Chat search with tag filtering now uses more efficient database queries, making filtered searches significantly faster. \u003ca href=\"https://github.com/open-webui/open-webui/commit/139f02a9d9fa2ffffcc96aa0de8af8ef51b6bcf2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eShared chat loading optimization.\u003c/strong\u003e The shared chats endpoint now loads only the needed columns instead of the full conversation history, making shared chat listings significantly faster. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21614\"\u003e#21614\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eArchived and pinned chat loading.\u003c/strong\u003e Loading archived and pinned chat lists is now significantly faster by loading only the needed columns instead of full conversation data. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21591\"\u003e#21591\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eChat title query optimization.\u003c/strong\u003e Retrieving chat titles now queries only the title column instead of the entire conversation history, making title lookups significantly faster and reducing database load. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21590\"\u003e#21590\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eBatch access grants for multiple resources.\u003c/strong\u003e Loading channels, knowledge bases, models, notes, prompts, skills, and tools now uses batch database queries for access grants instead of individual queries per item, significantly reducing database load. For 30 items, this reduces approximately 31 queries to just 3. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21616\"\u003e#21616\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eNotes list payload optimization.\u003c/strong\u003e Notes list and search endpoints now return only a 200-character preview instead of the full note content, reducing response payload from ~167 MB to ~10 KB for 60 notes and eliminating N+1 queries for access grants. The Notes tab now loads in seconds instead of tens of seconds. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21549\"\u003e#21549\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eTools list performance.\u003c/strong\u003e Loading the tools list is now significantly faster by deferring content and specs fields from database queries, and using cached tool modules instead of reloading them for each request. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b48594a16680cc77921a4ed1a11ffa07df7edc60\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eGroup description display.\u003c/strong\u003e The admin groups list now shows each group's description, making it easier for administrators to identify groups at a glance.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eSort by dropdown.\u003c/strong\u003e Administrators can now sort groups using a dropdown menu with options for Name or Members, replacing the previous clickable column headers.\u003c/li\u003e\n\u003cli\u003e📶 \u003cstrong\u003eAdmin groups list sorting.\u003c/strong\u003e The Group and Users columns in the admin groups list are now clickable for sorting, allowing administrators to sort groups alphabetically by name or numerically by member count. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21692\"\u003e#21692\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔽 \u003cstrong\u003eRich UI auto-scroll.\u003c/strong\u003e The view now automatically scrolls to action-generated Rich UI content once it renders, ensuring users can see the results without manually scrolling. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21698\"\u003e#21698\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21482\"\u003e#21482\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAdmin analytics toggle.\u003c/strong\u003e Administrators can now enable or disable the analytics feature using the ENABLE_ADMIN_ANALYTICS environment variable, giving more control over available admin features. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21651\"\u003e#21651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/35598b8017557258b8c9ee3469d320adb0140751\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAnalytics sorting enhancement.\u003c/strong\u003e The Analytics dashboard now supports sorting by Tokens column for both Model Usage and User Usage tables, and the Share/Percentage columns are now clickable for sorting. Administrators can more easily identify the most token-consuming models and users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/053a33631f575ae1ad3123190a9e820b4057f62d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📑 \u003cstrong\u003eFetch URL citation sources.\u003c/strong\u003e When models fetch URLs during tool calling, the fetched URLs now appear as clickable citation sources in the UI with content previews, matching the existing behavior of web search and knowledge file tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21669\"\u003e#21669\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eAdmin settings tab navigation.\u003c/strong\u003e The admin settings sidebar now supports native browser tab opening, allowing users to middle-click or right-click to open settings pages in new tabs. The navigation was converted from button-based to anchor-based elements. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21721\"\u003e#21721\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eModel visibility badges.\u003c/strong\u003e The Admin Settings Models page now displays Public or Private badges directly on each model, making it easy to identify model access levels at a glance without opening the edit screen. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21732\"\u003e#21732\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/29217cb430bd47827ebb20782b264ae7b0f233bb\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1ac3dd4a893e13803e7b889611303c4a7a5cc470\"\u003e\u003ccode\u003e1ac3dd4\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21773\"\u003e#21773\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/55c489146cf64d80630829a0ac98aa10c073925e\"\u003e\u003ccode\u003e55c4891\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ffcf97e3e1908c5c0879f5663f670981828d471c\"\u003e\u003ccode\u003effcf97e\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/95bde946ba4db0e6f88970e8507d5c404c53d6b1\"\u003e\u003ccode\u003e95bde94\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/895c805e626e59efe48518aca563b4870ba213af\"\u003e\u003ccode\u003e895c805\u003c/code\u003e\u003c/a\u003e feat: dictation toggle\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2ed3055c42ae18e3372081c18629963b0e244a62\"\u003e\u003ccode\u003e2ed3055\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21618\"\u003e#21618\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1792f668f2cff0beb7100a701965a73b3954c086\"\u003e\u003ccode\u003e1792f66\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1d3d3b2d94f016a4357470dcb89253379c43524c\"\u003e\u003ccode\u003e1d3d3b2\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9044abf3bb78eb6ce139102191b79b98cee654f1\"\u003e\u003ccode\u003e9044abf\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/424dba443c578008a1dfa0dd999069a12ab74a3a\"\u003e\u003ccode\u003e424dba4\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.43...v0.8.5\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.43\u0026new-version=0.8.5)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/darkhonor/helm-charts/pull/46","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/darkhonor%2Fhelm-charts/issues/46","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/46/packages"},{"uuid":"3967055636","node_id":"PR_kwDOPvrhr87FFpf3","number":42,"state":"closed","title":"Bump open-webui/open-webui from 0.6.43 to 0.8.3 in /charts/open-webui","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-02-24T07:28:26.000Z","author_association":null,"state_reason":null,"created_at":"2026-02-20T07:28:22.000Z","updated_at":"2026-02-24T07:28:28.000Z","time_to_close":345604,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.43","new_version":"0.8.3","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/charts/open-webui","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.43 to 0.8.3.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.3\u003c/h2\u003e\n\u003ch2\u003e[0.8.3] - 2026-02-17\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eModel edit shortcut.\u003c/strong\u003e Users can now edit models directly from the model selector dropdown menu, making it faster to modify model settings without navigating to separate admin or workspace pages. \u003ca href=\"https://github.com/open-webui/open-webui/commit/519ff40cb69cdc1d215cee369e9db70ff7438153\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eImage edit API background support.\u003c/strong\u003e The image edit API now supports the background parameter for OpenAI's gpt-image-1 model, enabling background transparency control (\u0026quot;transparent\u0026quot;, \u0026quot;opaque\u0026quot;, \u0026quot;auto\u0026quot;) when the feature is exposed in the UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21459\"\u003e#21459\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFaster model filtering.\u003c/strong\u003e Model access control filtering no longer makes a redundant database query to re-fetch model info that is already available in memory, reducing latency when loading model lists for non-admin users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/34cd3d79e8688f589e3dd2f03415f8a8f9a13115\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call display improvements.\u003c/strong\u003e Tool call results now display arguments in a cleaner key-value format instead of raw JSON, with a responsive layout that shows only the tool name on narrow screens and the full label on wider screens, preventing text wrapping to multiple lines. \u003ca href=\"https://github.com/open-webui/open-webui/commit/2ce935bdb10d2b26b230cd54cb649f5c667ed96a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eGeneral improvements.\u003c/strong\u003e Various improvements were implemented across the application to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📧 \u003cstrong\u003eUSER_EMAIL variable fix.\u003c/strong\u003e The {{USER_EMAIL}} template variable now correctly returns the user's email address instead of \u0026quot;Unknown\u0026quot; in prompts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21479\"\u003e#21479\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21465\"\u003e#21465\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage and file attachment handling fixes.\u003c/strong\u003e Uploaded images are now correctly sent to vision-enabled models, and file attachments now work even when no user text is entered alongside a system prompt. This fixes two issues where the backend was not properly processing file attachments: images weren't converted to the expected format for API requests, and file context was dropped when the user sent only a file without accompanying text. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1053d94c7ef7b8b78682dd73586b65a84d202a1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21477\"\u003e#21477\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21457\"\u003e#21457\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eMissing function error handling.\u003c/strong\u003e Models that reference deleted functions no longer cause the entire /api/models endpoint to crash; instead, the missing functions are skipped and logged, allowing the rest of the models to load successfully. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21476\"\u003e#21476\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21464\"\u003e#21464\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eStartup model pre-fetch error handling.\u003c/strong\u003e If model pre-fetching fails during app startup, the application now logs a warning and continues instead of crashing entirely. \u003ca href=\"https://github.com/open-webui/open-webui/commit/337109e99ce390f55a9085d0a301853637923779\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eFunction module loading error handling.\u003c/strong\u003e Function modules that fail to load during startup or model processing are now caught and logged, preventing crashes when models reference functions with loading errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/15b893e651de71b033408e1b713e0b51f6829ab8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003ePostgreSQL group query fix.\u003c/strong\u003e The '/api/v1/groups/' endpoint no longer fails with a GROUP BY error when using PostgreSQL; member counts are now calculated using correlated subqueries for better database compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21458\"\u003e#21458\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21467\"\u003e#21467\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.2\u003c/h2\u003e\n\u003ch2\u003e[0.8.2] - 2026-02-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eSkill content handling.\u003c/strong\u003e User-selected skills now have their full content injected into the chat, while model-attached skills only display name and description in the available skills list. This allows users to override skill behavior while model-attached skills remain flexible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/393c0071dc612c5ac982fb37dfc0288cb9911439\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eChat toggles now control built-in tools.\u003c/strong\u003e Users can now disable web search, image generation, and code execution on a per-conversation basis, even when those tools are enabled as builtin tools on the model. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20641\"\u003e#20641\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21318\"\u003e#21318\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c46ef3b63bcc1e2e9adbdd18fab82c4bbe33ff6c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1a1e64d2e9ad953b2bc2a9543e9a308b7c669c8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage preview in file modal.\u003c/strong\u003e Images uploaded to chats can now be previewed directly in the file management modal, making it easier to identify and manage image files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21413\"\u003e#21413\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e1b3e7252c1896c04d498547908f0fce111434e1\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eBatch tag operations.\u003c/strong\u003e Tag creation, deletion, and orphan cleanup for chats now use batch database queries instead of per-tag loops, significantly reducing database round trips when updating, archiving, or deleting chats with multiple tags. \u003ca href=\"https://github.com/open-webui/open-webui/commit/c748c3ede\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eFaster group list loading.\u003c/strong\u003e Group lists and search results now load with a single database query that joins member counts, replacing the previous pattern of fetching groups first and then counting members in a separate batch query. \u003ca href=\"https://github.com/open-webui/open-webui/commit/33308022f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eSkills sharing permissions.\u003c/strong\u003e Administrators can now control skills sharing and public sharing permissions per-group, matching the existing capabilities for tools, knowledge, and prompts. \u003ca href=\"https://github.com/open-webui/open-webui/commit/88401e91c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eLong content truncation in preview modals.\u003c/strong\u003e Citation and file content modals now truncate markdown-rendered content at 10,000 characters with a \u0026quot;Show all\u0026quot; expansion button, preventing UI jank when previewing very large documents.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eTranslation updates.\u003c/strong\u003e Translations for Spanish and German were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth session error handling.\u003c/strong\u003e Corrupted OAuth sessions are now gracefully handled and automatically cleaned up instead of causing errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7e224e4a536b07ec008613f06592e34050e7067c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eTask model selector validation.\u003c/strong\u003e The task model selector in admin settings now correctly accepts models based on the new access grants system instead of rejecting all models with an incorrect error. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a2595f0706d0c9d809ae7746001cf799f98db1d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eTool call message preservation.\u003c/strong\u003e Models no longer hallucinate tool outputs in multi-turn conversations because tool call history is now properly preserved instead of being merged into assistant messages. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21098\"\u003e#21098\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20600\"\u003e#20600\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f2aca781c87244cffc130aa2722e700c19a81d66\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool server startup initialization.\u003c/strong\u003e External tool servers configured via the \u0026quot;TOOL_SERVER_CONNECTIONS\u0026quot; environment variable now initialize automatically on startup, eliminating the need to manually visit the Admin Panel and save for tools to become available. This enables proper GitOps and containerized deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18140\"\u003e#18140\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/20914\"\u003e#20914\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f20cc6d7e6da493eb75ca1618f5cbd068fa57684\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e♻️ \u003cstrong\u003eResource handle cleanup.\u003c/strong\u003e File handles are now properly closed during audio transcription and pipeline uploads, preventing resource leaks that could cause system instability over time. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21411\"\u003e#21411\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eStrikethrough shortcut conflict fix.\u003c/strong\u003e Pressing Ctrl+Shift+S to toggle the sidebar no longer causes text to become struck through in the chat input, by disabling the TipTap Strike extension's default keyboard shortcut when rich text mode is off. \u003ca href=\"https://github.com/open-webui/open-webui/commit/38ae91ae2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call finish_reason fix.\u003c/strong\u003e API responses now correctly set finish_reason to \u0026quot;tool_calls\u0026quot; instead of \u0026quot;stop\u0026quot; when tool calls are present, fixing an issue where external API clients (such as OpenCode) would halt prematurely after tool execution when routing Ollama models through the Open WebUI API. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20896\"\u003e#20896\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.1\u003c/h2\u003e\n\u003ch2\u003e[0.8.1] - 2026-02-14\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!CAUTION]\n⚠️ \u003cstrong\u003eDatabase Migrations\u003c/strong\u003e: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.8.3] - 2026-02-17\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eModel edit shortcut.\u003c/strong\u003e Users can now edit models directly from the model selector dropdown menu, making it faster to modify model settings without navigating to separate admin or workspace pages. \u003ca href=\"https://github.com/open-webui/open-webui/commit/519ff40cb69cdc1d215cee369e9db70ff7438153\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eImage edit API background support.\u003c/strong\u003e The image edit API now supports the background parameter for OpenAI's gpt-image-1 model, enabling background transparency control (\u0026quot;transparent\u0026quot;, \u0026quot;opaque\u0026quot;, \u0026quot;auto\u0026quot;) when the feature is exposed in the UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21459\"\u003e#21459\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFaster model filtering.\u003c/strong\u003e Model access control filtering no longer makes a redundant database query to re-fetch model info that is already available in memory, reducing latency when loading model lists for non-admin users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/34cd3d79e8688f589e3dd2f03415f8a8f9a13115\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call display improvements.\u003c/strong\u003e Tool call results now display arguments in a cleaner key-value format instead of raw JSON, with a responsive layout that shows only the tool name on narrow screens and the full label on wider screens, preventing text wrapping to multiple lines. \u003ca href=\"https://github.com/open-webui/open-webui/commit/2ce935bdb10d2b26b230cd54cb649f5c667ed96a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eGeneral improvements.\u003c/strong\u003e Various improvements were implemented across the application to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📧 \u003cstrong\u003eUSER_EMAIL variable fix.\u003c/strong\u003e The {{USER_EMAIL}} template variable now correctly returns the user's email address instead of \u0026quot;Unknown\u0026quot; in prompts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21479\"\u003e#21479\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21465\"\u003e#21465\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage and file attachment handling fixes.\u003c/strong\u003e Uploaded images are now correctly sent to vision-enabled models, and file attachments now work even when no user text is entered alongside a system prompt. This fixes two issues where the backend was not properly processing file attachments: images weren't converted to the expected format for API requests, and file context was dropped when the user sent only a file without accompanying text. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1053d94c7ef7b8b78682dd73586b65a84d202a1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21477\"\u003e#21477\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21457\"\u003e#21457\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eMissing function error handling.\u003c/strong\u003e Models that reference deleted functions no longer cause the entire /api/models endpoint to crash; instead, the missing functions are skipped and logged, allowing the rest of the models to load successfully. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21476\"\u003e#21476\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21464\"\u003e#21464\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eStartup model pre-fetch error handling.\u003c/strong\u003e If model pre-fetching fails during app startup, the application now logs a warning and continues instead of crashing entirely. \u003ca href=\"https://github.com/open-webui/open-webui/commit/337109e99ce390f55a9085d0a301853637923779\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eFunction module loading error handling.\u003c/strong\u003e Function modules that fail to load during startup or model processing are now caught and logged, preventing crashes when models reference functions with loading errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/15b893e651de71b033408e1b713e0b51f6829ab8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003ePostgreSQL group query fix.\u003c/strong\u003e The '/api/v1/groups/' endpoint no longer fails with a GROUP BY error when using PostgreSQL; member counts are now calculated using correlated subqueries for better database compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21458\"\u003e#21458\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21467\"\u003e#21467\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.8.2] - 2026-02-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eSkill content handling.\u003c/strong\u003e User-selected skills now have their full content injected into the chat, while model-attached skills only display name and description in the available skills list. This allows users to override skill behavior while model-attached skills remain flexible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/393c0071dc612c5ac982fb37dfc0288cb9911439\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eChat toggles now control built-in tools.\u003c/strong\u003e Users can now disable web search, image generation, and code execution on a per-conversation basis, even when those tools are enabled as builtin tools on the model. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20641\"\u003e#20641\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21318\"\u003e#21318\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c46ef3b63bcc1e2e9adbdd18fab82c4bbe33ff6c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1a1e64d2e9ad953b2bc2a9543e9a308b7c669c8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage preview in file modal.\u003c/strong\u003e Images uploaded to chats can now be previewed directly in the file management modal, making it easier to identify and manage image files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21413\"\u003e#21413\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e1b3e7252c1896c04d498547908f0fce111434e1\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eBatch tag operations.\u003c/strong\u003e Tag creation, deletion, and orphan cleanup for chats now use batch database queries instead of per-tag loops, significantly reducing database round trips when updating, archiving, or deleting chats with multiple tags. \u003ca href=\"https://github.com/open-webui/open-webui/commit/c748c3ede\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eFaster group list loading.\u003c/strong\u003e Group lists and search results now load with a single database query that joins member counts, replacing the previous pattern of fetching groups first and then counting members in a separate batch query. \u003ca href=\"https://github.com/open-webui/open-webui/commit/33308022f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eSkills sharing permissions.\u003c/strong\u003e Administrators can now control skills sharing and public sharing permissions per-group, matching the existing capabilities for tools, knowledge, and prompts. \u003ca href=\"https://github.com/open-webui/open-webui/commit/88401e91c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eLong content truncation in preview modals.\u003c/strong\u003e Citation and file content modals now truncate markdown-rendered content at 10,000 characters with a \u0026quot;Show all\u0026quot; expansion button, preventing UI jank when previewing very large documents.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eTranslation updates.\u003c/strong\u003e Translations for Spanish and German were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth session error handling.\u003c/strong\u003e Corrupted OAuth sessions are now gracefully handled and automatically cleaned up instead of causing errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7e224e4a536b07ec008613f06592e34050e7067c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eTask model selector validation.\u003c/strong\u003e The task model selector in admin settings now correctly accepts models based on the new access grants system instead of rejecting all models with an incorrect error. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a2595f0706d0c9d809ae7746001cf799f98db1d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eTool call message preservation.\u003c/strong\u003e Models no longer hallucinate tool outputs in multi-turn conversations because tool call history is now properly preserved instead of being merged into assistant messages. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21098\"\u003e#21098\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20600\"\u003e#20600\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f2aca781c87244cffc130aa2722e700c19a81d66\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool server startup initialization.\u003c/strong\u003e External tool servers configured via the \u0026quot;TOOL_SERVER_CONNECTIONS\u0026quot; environment variable now initialize automatically on startup, eliminating the need to manually visit the Admin Panel and save for tools to become available. This enables proper GitOps and containerized deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18140\"\u003e#18140\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/20914\"\u003e#20914\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f20cc6d7e6da493eb75ca1618f5cbd068fa57684\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e♻️ \u003cstrong\u003eResource handle cleanup.\u003c/strong\u003e File handles are now properly closed during audio transcription and pipeline uploads, preventing resource leaks that could cause system instability over time. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21411\"\u003e#21411\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eStrikethrough shortcut conflict fix.\u003c/strong\u003e Pressing Ctrl+Shift+S to toggle the sidebar no longer causes text to become struck through in the chat input, by disabling the TipTap Strike extension's default keyboard shortcut when rich text mode is off. \u003ca href=\"https://github.com/open-webui/open-webui/commit/38ae91ae2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call finish_reason fix.\u003c/strong\u003e API responses now correctly set finish_reason to \u0026quot;tool_calls\u0026quot; instead of \u0026quot;stop\u0026quot; when tool calls are present, fixing an issue where external API clients (such as OpenCode) would halt prematurely after tool execution when routing Ollama models through the Open WebUI API. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20896\"\u003e#20896\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.8.1] - 2026-02-14\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eChannel user active status.\u003c/strong\u003e Checking user active status in channels is now faster thanks to optimized database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/ca6b18ab5cb94153a9dae233f975d36bf6b19b76\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eResponses API endpoint with model routing.\u003c/strong\u003e The OpenAI API proxy now supports a /responses endpoint that routes requests to the correct backend based on the model field in the request, instead of always using the first configured endpoint. This enables support for backends like vLLM that provide /skills and /v1/responses endpoints. \u003ca href=\"https://github.com/open-webui/open-webui/commit/abc9b63093d65f4d74342db85b7d5df1809aa0f0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/79ecbfc757f0642740d0e44fab98263d84295490\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eModel and prompt list optimization.\u003c/strong\u003e Improved performance when loading models and prompts by pre-fetching user group IDs once instead of making multiple database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/20de5a87da0c12e4052b50887a42ddd7228c5ef5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b8112d72b95e480f946f0688bed29321b61e65af\"\u003e\u003ccode\u003eb8112d7\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21507\"\u003e#21507\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/71ccedd2bf9cd6b831718cd556e74b4bb0633c4c\"\u003e\u003ccode\u003e71ccedd\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4225791313f003c85bdd7bd21e49879404359f3c\"\u003e\u003ccode\u003e4225791\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21458\"\u003e#21458\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e5cd1b479b641430ae53027af3648499aab836aa\"\u003e\u003ccode\u003ee5cd1b4\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/61d44aa773771127e1caa6c35cc322f8962adc13\"\u003e\u003ccode\u003e61d44aa\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ef036529b55c0e94c874dc6c16a2c0e5345dc542\"\u003e\u003ccode\u003eef03652\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e0bdef85abad22b01fe21ceeba96f1af4300cbed\"\u003e\u003ccode\u003ee0bdef8\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2ce935bdb10d2b26b230cd54cb649f5c667ed96a\"\u003e\u003ccode\u003e2ce935b\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/23b1e2cca475f2a6099c1d4d032b92dccc33f435\"\u003e\u003ccode\u003e23b1e2c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/05b8768fb9df2f079591f91fd544ad5793c793a5\"\u003e\u003ccode\u003e05b8768\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.43...v0.8.3\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.43\u0026new-version=0.8.3)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/darkhonor/helm-charts/pull/42","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/darkhonor%2Fhelm-charts/issues/42","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/42/packages"},{"uuid":"3946294355","node_id":"PR_kwDOPIpjyc7EBdRm","number":24,"state":"closed","title":"Bump open-webui/open-webui from 0.7.2-slim to 0.8.1-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-02-17T07:15:26.000Z","author_association":null,"state_reason":null,"created_at":"2026-02-16T07:21:10.000Z","updated_at":"2026-02-17T07:15:27.000Z","time_to_close":86056,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.7.2-slim","new_version":"0.8.1-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.7.2-slim to 0.8.1-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.1\u003c/h2\u003e\n\u003ch2\u003e[0.8.1] - 2026-02-14\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!CAUTION]\n⚠️ \u003cstrong\u003eDatabase Migrations\u003c/strong\u003e: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eChannel user active status.\u003c/strong\u003e Checking user active status in channels is now faster thanks to optimized database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/ca6b18ab5cb94153a9dae233f975d36bf6b19b76\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eResponses API endpoint with model routing.\u003c/strong\u003e The OpenAI API proxy now supports a /responses endpoint that routes requests to the correct backend based on the model field in the request, instead of always using the first configured endpoint. This enables support for backends like vLLM that provide /skills and /v1/responses endpoints. \u003ca href=\"https://github.com/open-webui/open-webui/commit/abc9b63093d65f4d74342db85b7d5df1809aa0f0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/79ecbfc757f0642740d0e44fab98263d84295490\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eModel and prompt list optimization.\u003c/strong\u003e Improved performance when loading models and prompts by pre-fetching user group IDs once instead of making multiple database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/20de5a87da0c12e4052b50887a42ddd7228c5ef5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eBatch access control queries.\u003c/strong\u003e Improved performance when loading models, prompts, and knowledge bases by replacing multiple individual access checks with single batch queries, significantly reducing database load for large deployments. \u003ca href=\"https://github.com/open-webui/open-webui/commit/589c4e64c1b7bb7a7a5abc20382b92fb860e28c2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eFaster user list loading.\u003c/strong\u003e User lists now load significantly faster by deferring profile image loading; images are fetched separately in parallel by the browser, improving caching and reducing database load. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b7549d2f6ca2843661ec79a5a1e55da9e7553368\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eWeb search result count.\u003c/strong\u003e The built-in search_web tool now respects the admin-configured \u0026quot;Search Result Count\u0026quot; setting instead of always returning 5 results when using Native Function Calling mode. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21373\"\u003e#21373\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21371\"\u003e#21371\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eSCIM externalId support.\u003c/strong\u003e SCIM-enabled deployments can now store and manage externalId for user provisioning, enabling better integration with identity providers like Microsoft Entra ID and Okta. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21099\"\u003e#21099\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21280\"\u003e#21280\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/d1d1efe212b16e0052359991d67fd813125077e8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eTranslation updates.\u003c/strong\u003e Portuguese (Brazil) translations were updated.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003ePublic sharing security fix.\u003c/strong\u003e Fixed a security issue where users with write access could see the Public sharing option regardless of their actual public sharing permission, and direct API calls could bypass frontend sharing restrictions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21358\"\u003e#21358\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21356\"\u003e#21356\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eDirect model access control fix.\u003c/strong\u003e Model access control changes now persist correctly for direct Ollama and OpenAI models that don't have database entries, and error messages display properly instead of showing \u0026quot;[object Object]\u0026quot;. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f027a01ab2ff3b6175af3dd13a4478c265c0544a\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21377\"\u003e#21377\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💭 \u003cstrong\u003eReasoning trace rendering performance.\u003c/strong\u003e Reasoning traces from models now render properly without being split into many fragments, preventing browser slowdowns during streaming responses. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21348\"\u003e#21348\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/3b61562c82448cf83710d8b6ed29b797991aa83a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eARM device compatibility fix.\u003c/strong\u003e Fixed an issue where upgrading to 0.8.0 would fail to start on ARM devices (like Raspberry Pi 4) due to torch 2.10.0 causing SIGILL errors; now pinned to torch\u0026lt;=2.9.1. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21385\"\u003e#21385\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21349\"\u003e#21349\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eSkills PostgreSQL compatibility fix.\u003c/strong\u003e Fixed a PostgreSQL compatibility issue where creating or listing skills would fail with a TypeError, while SQLite worked correctly. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21372\"\u003e#21372\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b4c3f54f9648c4232a0fd6557703ffa66fcf4caa\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21365\"\u003e#21365\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003ePostgreSQL analytics query fix.\u003c/strong\u003e Fixed an issue where retrieving chat IDs by model ID would fail on PostgreSQL due to incompatible DISTINCT ordering, while SQLite worked correctly. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21347\"\u003e#21347\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/7bda6bf767d5d5c4dc1111465096a88e10b5030e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗃️ \u003cstrong\u003eSQLite cascade delete fix.\u003c/strong\u003e Deleting chats now properly removes all associated messages in SQLite, matching PostgreSQL behavior and preventing orphaned data. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21362\"\u003e#21362\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ \u003cstrong\u003eOllama Cloud model naming fix.\u003c/strong\u003e Fixed an issue where using Ollama Cloud models would fail with \u0026quot;Model not found\u0026quot; errors because \u0026quot;:latest\u0026quot; was incorrectly appended to model names. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21386\"\u003e#21386\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eKnowledge selector tooltip z-index.\u003c/strong\u003e Fixed an issue where tooltips in the \u0026quot;Select Knowledge\u0026quot; dropdown were hidden behind the menu, making it difficult to read knowledge item names and descriptions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21375\"\u003e#21375\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eModel selector scroll position.\u003c/strong\u003e The model selector dropdown now correctly scrolls to and centers the currently selected model when opened, and resets scroll position when reopened. \u003ca href=\"https://github.com/open-webui/open-webui/commit/0b05b2fc7ed4c38af158707438ff404d1beb7c91\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eSync modal unexpected appearance.\u003c/strong\u003e Fixed an issue where the Sync Modal would appear unexpectedly after enabling the \u0026quot;Community Sharing\u0026quot; feature if the user had previously visited the app with the sync parameter. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21376\"\u003e#21376\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eKnowledge collection layout fix.\u003c/strong\u003e Fixed a layout issue in the Knowledge integration menu where long collection names caused indentation artifacts and now properly truncate with ellipsis. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21374\"\u003e#21374\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eMetadata processing crash fix.\u003c/strong\u003e Fixed a latent bug where processing document metadata containing certain keys (content, pages, tables, paragraphs, sections, figures) would cause a RuntimeError due to dictionary mutation during iteration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21105\"\u003e#21105\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003ePassword validation regex fix.\u003c/strong\u003e Fixed the password validation regex by adding the raw string prefix, ensuring escape sequences like d and w are interpreted correctly. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21400\"\u003e#21400\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21399\"\u003e#21399\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚠️ \u003cstrong\u003eDatabase Migrations:\u003c/strong\u003e This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.0\u003c/h2\u003e\n\u003ch2\u003e[0.8.0] - 2026-02-12\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!CAUTION]\n⚠️ \u003cstrong\u003eDatabase Migrations\u003c/strong\u003e: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!WARNING]\n⚠️ \u003cstrong\u003eLong-Running Database Migration\u003c/strong\u003e: This release includes a migration for the \u003ccode\u003echat_message\u003c/code\u003e table that can take a significant amount of time to complete, especially in larger deployments with extensive chat histories. Please plan for adequate downtime and allow the migration to finish completely without interruption.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/883f1dda0f18fbe26aca7aed5a8804021a3685ca\"\u003e\u003ccode\u003e883f1dd\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21346\"\u003e#21346\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/12bad452fa409121effae088316fa2a29ae48541\"\u003e\u003ccode\u003e12bad45\u003c/code\u003e\u003c/a\u003e chore: Changelog updates (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21382\"\u003e#21382\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5de60dc922a74c9ce6cf5b2de3129e4ca3d9ffdd\"\u003e\u003ccode\u003e5de60dc\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a30b106ea3ac64a62ef3a3457689c402c833d6e5\"\u003e\u003ccode\u003ea30b106\u003c/code\u003e\u003c/a\u003e fix issues/21399 (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21400\"\u003e#21400\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d33ad462aa6f2105f0d118ab6f2fd74f693c8680\"\u003e\u003ccode\u003ed33ad46\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/3b61562c82448cf83710d8b6ed29b797991aa83a\"\u003e\u003ccode\u003e3b61562\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e5d88be4f3896f3407d762d4b2a24e0bb7447f06\"\u003e\u003ccode\u003ee5d88be\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b36f8d9314e2a127b88d521a53c804a7cdee4b48\"\u003e\u003ccode\u003eb36f8d9\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/626d236d137915aee090d8a82dc0a57fbc22424b\"\u003e\u003ccode\u003e626d236\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/79ecbfc757f0642740d0e44fab98263d84295490\"\u003e\u003ccode\u003e79ecbfc\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.7.2...v0.8.1\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.7.2-slim\u0026new-version=0.8.1-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/24","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/24","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/24/packages"},{"uuid":"3657450130","node_id":"PR_kwDOPIpjyc61H4Jz","number":16,"state":"closed","title":"Bump open-webui/open-webui from v0.6.36-slim to v0.6.37-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-11-25T07:21:31.000Z","author_association":null,"state_reason":null,"created_at":"2025-11-24T07:27:53.000Z","updated_at":"2025-11-25T07:21:32.000Z","time_to_close":86018,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.6.36-slim","new_version":"v0.6.37-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.6.36-slim to v0.6.37-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.37\u003c/h2\u003e\n\u003ch2\u003e[0.6.37] - 2025-11-24\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔐 Granular sharing permissions are now available with two-tiered control separating group sharing from public sharing, allowing administrators to independently configure whether users can share workspace items with groups or make them publicly accessible, with separate permission toggles for models, knowledge bases, prompts, tools, and notes, configurable via \u0026quot;USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_SHARING\u0026quot;, \u0026quot;USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING\u0026quot;, and corresponding environment variables for other workspace item types, while groups can now be configured to opt-out of sharing via the \u0026quot;Allow Group Sharing\u0026quot; setting. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7be750bcbb40da91912a0a66b7ab791effdcc3b6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f69e37a8507d6d57382d6670641b367f3127f90a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Password policy enforcement is now available with configurable validation rules, allowing administrators to require specific password complexity requirements via \u0026quot;ENABLE_PASSWORD_VALIDATION\u0026quot; and \u0026quot;PASSWORD_VALIDATION_REGEX_PATTERN\u0026quot; environment variables, with default pattern requiring minimum 8 characters including uppercase, lowercase, digit, and special character. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17794\"\u003e#17794\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Granular import and export permissions are now available for workspace items, introducing six separate permission toggles for models, prompts, and tools that are disabled by default for enhanced security. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19242\"\u003e#19242\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Default group assignment is now available for new users, allowing administrators to automatically assign newly registered users to a specified group for streamlined access control to models, prompts, and tools, particularly useful for organizations with group-based model access policies. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19325\"\u003e#19325\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17842\"\u003e#17842\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Password-based authentication can now be fully disabled via \u0026quot;ENABLE_PASSWORD_AUTH\u0026quot; environment variable, enforcing SSO-only authentication and preventing password login fallback when SSO is configured. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19113\"\u003e#19113\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ Large stream chunk handling was implemented to support models that generate images directly in their output responses, with configurable buffer size via \u0026quot;CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE\u0026quot; environment variable, resolving compatibility issues with models like Gemini 2.5 Flash Image. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18884\"\u003e#18884\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17626\"\u003e#17626\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ Streaming response middleware now handles images in delta updates with automatic base64 conversion, enabling proper display of images from models using the \u0026quot;choices[0].delta.images.image_url\u0026quot; format such as Gemini 2.5 Flash Image Preview on OpenRouter. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19073\"\u003e#19073\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19019\"\u003e#19019\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📈 Model list API performance was optimized by pre-fetching user group memberships and removing profile image URLs from response payloads, significantly reducing both database queries and payload size for instances with large model lists, with profile images now served dynamically via dedicated endpoints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19097\"\u003e#19097\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18950\"\u003e#18950\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⏩ Batch file processing performance was improved by reducing database queries by 67% while ensuring data consistency between vector and relational databases. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18953\"\u003e#18953\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 Chat import performance was dramatically improved by replacing individual per-chat API requests with a bulk import endpoint, reducing import time by up to 95% for large chat collections and providing user feedback via toast notifications displaying the number of successfully imported chats. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17861\"\u003e#17861\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Socket event broadcasting performance was optimized by implementing user-specific rooms, significantly reducing server overhead particularly for users with multiple concurrent sessions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18996\"\u003e#18996\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ Weaviate is now supported as a vector database option, providing an additional choice for RAG document storage alongside existing ChromaDB, Milvus, Qdrant, and OpenSearch integrations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/14747\"\u003e#14747\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ PostgreSQL pgvector now supports HNSW index types and large dimensional embeddings exceeding 2000 dimensions through automatic halfvec type selection, with configurable index methods via \u0026quot;PGVECTOR_INDEX_METHOD\u0026quot;, \u0026quot;PGVECTOR_HNSW_M\u0026quot;, \u0026quot;PGVECTOR_HNSW_EF_CONSTRUCTION\u0026quot;, and \u0026quot;PGVECTOR_IVFFLAT_LISTS\u0026quot; environment variables. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19158\"\u003e#19158\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16890\"\u003e#16890\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Azure AI Search is now supported as a web search provider, enabling integration with Azure's cognitive search services via \u0026quot;AZURE_AI_SEARCH_API_KEY\u0026quot;, \u0026quot;AZURE_AI_SEARCH_ENDPOINT\u0026quot;, and \u0026quot;AZURE_AI_SEARCH_INDEX_NAME\u0026quot; configuration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19104\"\u003e#19104\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ External embedding generation now processes API requests in parallel instead of sequential batches, reducing document processing time by 10-50x when using OpenAI, Azure OpenAI, or Ollama embedding providers, with large PDFs now processing in seconds instead of minutes. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19296\"\u003e#19296\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 Base64 image conversion is now available for markdown content in chat responses, automatically uploading embedded images exceeding 1KB and replacing them with file URLs to reduce payload size and resource consumption, configurable via \u0026quot;REPLACE_IMAGE_URLS_IN_CHAT_RESPONSE\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19076\"\u003e#19076\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 OpenAI image generation now supports additional API parameters including quality settings for GPT Image 1, configurable via \u0026quot;IMAGES_OPENAI_API_PARAMS\u0026quot; environment variable or through the admin interface, enabling cost-effective image generation with low, medium, or high quality options. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19228\"\u003e#19228\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ Image editing can now be independently enabled or disabled via admin settings, allowing administrators to control whether sequential image prompts trigger image editing or new image generation, configurable via \u0026quot;ENABLE_IMAGE_EDIT\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19284\"\u003e#19284\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 SSRF protection was implemented with a configurable URL blocklist that prevents access to cloud metadata endpoints and private networks, with default protections for AWS, Google Cloud, Azure, and Alibaba Cloud metadata services, customizable via \u0026quot;WEB_FETCH_FILTER_LIST\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19201\"\u003e#19201\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Workspace models page now supports server-side pagination dramatically improving load times and usability for instances with large numbers of workspace models.\u003c/li\u003e\n\u003cli\u003e🔍 Hybrid search now indexes file metadata including filenames, titles, headings, sources, and snippets alongside document content, enabling keyword queries to surface documents where search terms appear only in metadata, configurable via \u0026quot;ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19095\"\u003e#19095\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📂 Knowledge base upload page now supports folder drag-and-drop with recursive directory handling, enabling batch uploads of entire directory structures instead of requiring individual file selection. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19320\"\u003e#19320\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🤖 Model cloning is now available in admin settings, allowing administrators to quickly create workspace models based on existing base models through a \u0026quot;Clone\u0026quot; option in the model dropdown menu. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17937\"\u003e#17937\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 UI scale adjustment is now available in interface settings, allowing users to increase the size of the entire interface from 1.0x to 1.5x for improved accessibility and readability, particularly beneficial for users with visual impairments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19186\"\u003e#19186\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📌 Default pinned models can now be configured by administrators for all new users, mirroring the behavior of default models where admin-configured defaults apply only to users who haven't customized their pinned models, configurable via \u0026quot;DEFAULT_PINNED_MODELS\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19273\"\u003e#19273\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎙️ Text-to-Speech and Speech-to-Text services now receive user information headers when \u0026quot;ENABLE_FORWARD_USER_INFO_HEADERS\u0026quot; is enabled, allowing external TTS and STT providers to implement user-specific personalization, rate limiting, and usage tracking. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19323\"\u003e#19323\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19312\"\u003e#19312\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎙️ Voice mode now supports custom system prompts via \u0026quot;VOICE_MODE_PROMPT_TEMPLATE\u0026quot; configuration, allowing administrators to control response style and behavior for voice interactions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18607\"\u003e#18607\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 WebSocket and Redis configuration options are now available including debug logging controls, custom ping timeout and interval settings, and arbitrary Redis connection options via \u0026quot;WEBSOCKET_SERVER_LOGGING\u0026quot;, \u0026quot;WEBSOCKET_SERVER_ENGINEIO_LOGGING\u0026quot;, \u0026quot;WEBSOCKET_SERVER_PING_TIMEOUT\u0026quot;, \u0026quot;WEBSOCKET_SERVER_PING_INTERVAL\u0026quot;, and \u0026quot;WEBSOCKET_REDIS_OPTIONS\u0026quot; environment variables. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19091\"\u003e#19091\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 MCP OAuth dynamic client registration now automatically detects and uses the appropriate token endpoint authentication method from server-supported options, enabling compatibility with OAuth servers that only support \u0026quot;client_secret_basic\u0026quot; instead of \u0026quot;client_secret_post\u0026quot;. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19193\"\u003e#19193\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 Custom headers can now be configured for remote MCP and OpenAPI tool server connections, enabling integration with services that require additional authentication headers. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18918\"\u003e#18918\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Perplexity Search now supports custom API endpoints via \u0026quot;PERPLEXITY_SEARCH_API_URL\u0026quot; configuration and automatically forwards user information headers to enable personalized search experiences. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19147\"\u003e#19147\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 User information headers can now be optionally forwarded to external web search engines when \u0026quot;ENABLE_FORWARD_USER_INFO_HEADERS\u0026quot; is enabled. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19043\"\u003e#19043\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Daily active user metric is now available for monitoring, tracking unique users active since midnight UTC via the \u0026quot;webui.users.active.today\u0026quot; Prometheus gauge. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19236\"\u003e#19236\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19234\"\u003e#19234\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Audit log file path is now configurable via \u0026quot;AUDIT_LOGS_FILE_PATH\u0026quot; environment variable, enabling storage in separate volumes or custom locations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19173\"\u003e#19173\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Sidebar collapse states for model lists and group information are now persistent across page refreshes, remembering user preferences through browser-based storage. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19159\"\u003e#19159\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Background image display was enhanced with semi-transparent overlays for navbar and sidebar, creating a seamless and visually cohesive design across the entire interface. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19157\"\u003e#19157\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 Tables in chat messages now include a copy button that appears on hover, enabling quick copying of table content alongside the existing CSV export functionality. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19162\"\u003e#19162\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Notes can now be created directly via the \u0026quot;/notes/new\u0026quot; URL endpoint with optional title and content query parameters, enabling faster note creation through bookmarks and shortcuts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19195\"\u003e#19195\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ Tag suggestions are now context-aware, displaying only relevant tags when creating or editing models versus chat conversations, preventing confusion between model and chat tags. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19135\"\u003e#19135\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✍️ Prompt autocompletion is now available independently of the rich text input setting, improving accessibility to the feature. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19150\"\u003e#19150\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Simplified Chinese, Traditional Chinese, Portuguese (Brazil), Catalan, Spanish (Spain), Finnish, Irish, Farsi, Swedish, Danish, German, Korean, and Thai were improved and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/fe6783c16699911c7be17392596d579333fb110c\"\u003e\u003ccode\u003efe6783c\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19030\"\u003e#19030\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a91663c5041ef8ee48dd411619e65c9061c64d6e\"\u003e\u003ccode\u003ea91663c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1e01836c08585f0d969d360d8e95ab1e192bf4f6\"\u003e\u003ccode\u003e1e01836\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/97f5c214859df383317558c3999eaf3d5f67d891\"\u003e\u003ccode\u003e97f5c21\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9d14bc2a8dcaa228bd018c9b2d8dfca8e4e39f89\"\u003e\u003ccode\u003e9d14bc2\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4857c69bd304900869d793d3e57f5f7545108c6b\"\u003e\u003ccode\u003e4857c69\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/de889f5ec7963c4eca33dcba51e08b5a755b46f3\"\u003e\u003ccode\u003ede889f5\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0259312626dee07d505b5f6d4f8594198c2662a1\"\u003e\u003ccode\u003e0259312\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5af5e1d3e4e4e3f9d10e37d718a63efc00be54c7\"\u003e\u003ccode\u003e5af5e1d\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2e1ddf823b1c59d8ae968ab5ca264d42a64c9dc8\"\u003e\u003ccode\u003e2e1ddf8\u003c/code\u003e\u003c/a\u003e refac: prompt suggestions component\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.36...v0.6.37\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.6.36-slim\u0026new-version=v0.6.37-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/16","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/16","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/16/packages"},{"uuid":"2879842001","node_id":"PR_kwDONjNt7s6rpubR","number":8,"state":"open","title":"Bump open-webui/open-webui from `2466939` to `c77fa8d`","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-10-01T22:15:59.000Z","updated_at":"2025-10-01T22:15:59.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"`2466939`","new_version":"`c77fa8d`","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from `2466939` to `c77fa8d`.\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch1\u003eChangelog\u003c/h1\u003e\n\u003cp\u003eAll notable changes to this project will be documented in this file.\u003c/p\u003e\n\u003cp\u003eThe format is based on \u003ca href=\"https://keepachangelog.com/en/1.1.0/\"\u003eKeep a Changelog\u003c/a\u003e,\nand this project adheres to \u003ca href=\"https://semver.org/spec/v2.0.0.html\"\u003eSemantic Versioning\u003c/a\u003e.\u003c/p\u003e\n\u003ch2\u003e[0.6.32] - 2025-09-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ JSON model import moved to backend processing for significant performance improvements when importing large model files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17871\"\u003e#17871\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚠️ Visual warnings for group permissions that display when a permission is disabled in a group but remains enabled in the default user role, clarifying inheritance behavior for administrators. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17848\"\u003e#17848\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ Milvus multi-tenancy mode using shared collections with resource ID filtering for improved scalability, mirroring the existing Qdrant implementation and configurable via ENABLE_MILVUS_MULTITENANCY_MODE environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17837\"\u003e#17837\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Enhanced tool result processing with improved error handling, better MCP tool result handling, and performance improvements for embedded UI components. \u003ca href=\"https://github.com/open-webui/open-webui/commit/4f06f29348b2c9d71c87d1bbe5b748a368f5101f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 New user groups now automatically inherit default group permissions, streamlining the admin setup process by eliminating manual permission configuration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17843\"\u003e#17843\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗂️ Bulk unarchive functionality for all chats, providing a single backend endpoint to efficiently restore all archived chats at once. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17857\"\u003e#17857\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ Browser tab title toggle setting allows users to control whether chat titles appear in the browser tab or display only \u0026quot;Open WebUI\u0026quot;. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17851\"\u003e#17851\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Reply-to-message functionality in channels, allowing users to reply directly to specific messages with visual threading and context display. \u003ca href=\"https://github.com/open-webui/open-webui/commit/1a18928c94903ad1f1f0391b8ade042c3e60205b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 Tool server import and export functionality, allowing direct upload of openapi.json and openapi.yaml files as an alternative to URL-based configuration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14446\"\u003e#14446\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 User valve configuration for Functions is now available in the integration menu, providing consistent management alongside Tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17784\"\u003e#17784\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Admin permission toggle for controlling public sharing of notes, configurable via USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17801\"\u003e#17801\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/715\"\u003e#715\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/715\"\u003eopen-webui/docs#715\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🗄️ DISKANN index type support for Milvus vector database with configurable maximum degree and search list size parameters. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17770\"\u003e#17770\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/docs/commit/cec50ab4d4b659558ca1ccd4b5e6fc024f05fb83\"\u003eDocs:Commit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Chinese (Simplified \u0026amp; Traditional) and Bosnian (Latin) were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛠️ MCP tool calls are now correctly routed to the appropriate server when multiple streamable-http MCP servers are enabled, preventing \u0026quot;Tool not found\u0026quot; errors. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17817\"\u003e#17817\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ External tool servers (OpenAPI/MCP) now properly process and return tool results to the model, restoring functionality that was broken in v0.6.31. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17764\"\u003e#17764\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 User valve detection now correctly identifies valves in imported tool code, ensuring gear icons appear in the integrations menu for all tools with user valves. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17765\"\u003e#17765\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 MCP OAuth discovery now correctly handles multi-tenant configurations by including subpaths in metadata URL discovery. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17768\"\u003e#17768\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ Milvus query operations now correctly use -1 instead of None for unlimited queries, preventing TypeError exceptions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17769\"\u003e#17769\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17088\"\u003e#17088\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 File upload error messages are now displayed when files are modified during upload, preventing user confusion on Android and Windows devices. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17777\"\u003e#17777\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 MessageInput Integrations button hover effect now displays correctly with proper visual feedback. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17767\"\u003e#17767\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u0026quot;Set as default\u0026quot; label positioning is fixed to ensure it remains clickable in all scenarios, including multi-model configurations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17779\"\u003e#17779\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎛️ Floating buttons now correctly retrieve message context by using the proper messageId parameter in createMessagesList calls. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17823\"\u003e#17823\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📌 Pinned chats are now properly cleared from the sidebar after archiving all chats, ensuring UI consistency without requiring a page refresh. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17832\"\u003e#17832\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ Delete confirmation modals now properly truncate long names for Notes, Prompts, Tools, and Functions to prevent modal overflow. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17812\"\u003e#17812\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🌐 Internationalization function calls now use proper Svelte store subscription syntax, preventing \u0026quot;i18n.t is not a function\u0026quot; errors on the model creation page. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17819\"\u003e#17819\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Playground chat interface button layout is corrected to prevent vertical text rendering for Assistant/User role buttons. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17819\"\u003e#17819\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ UI text truncation is improved across multiple components including usernames in admin panels, arena model names, model tags, and filter tags to prevent layout overflow issues. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17805\"\u003e#17805\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17803\"\u003e#17803\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17791\"\u003e#17791\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17796\"\u003e#17796\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.31] - 2025-09-25\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔌 MCP (streamable HTTP) server support was added alongside existing OpenAPI server integration, allowing users to connect both server types through an improved server configuration interface. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15932\"\u003e#15932\u003c/a\u003e \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/16651\"\u003e#16651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/777e81f7a8aca957a359d51df8388e5af4721a68\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/de7f7b3d855641450f8e5aac34fbae0665e0b80e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1bbf3a91e4713039364b790e886e59b401572d0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c55afc42559c32a6f0c8beb0f1bb18e9360ab8af\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/61f20acf61f4fe30c0e5b0180949f6e1a8cf6524\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 To enable MCP server authentication, OAuth 2.1 dynamic client registration was implemented with secure automatic client registration, encrypted session management, and seamless authentication flows. \u003ca href=\"https://github.com/open-webui/open-webui/commit/972be4eda5a394c111e849075f94099c9c0dd9aa\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/77e971dd9fbeee806e2864e686df5ec75e82104b\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/879abd7feea3692a2f157da4a458d30f27217508\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/422d38fd114b1ebd8a7dbb114d64e14791e67d7a\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/709\"\u003e#709\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/709\"\u003eopen-webui/docs#709\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🛠️ External \u0026amp; Built-In Tools can now support rich UI element embedding (\u003ca href=\"https://docs.openwebui.com/features/plugin/tools/development\"\u003eDocs\u003c/a\u003e), allowing tools to return HTML content and interactive iframes that display directly within chat conversations with configurable security settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/07c5b25bc8b63173f406feb3ba183d375fedee6a\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a5d8882bba7933a2c2c31c0a1405aba507c370bb\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/7be5b7f50f498de97359003609fc5993a172f084\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a89ffccd7e96705a4a40e845289f4fcf9c4ae596\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003eSee full diff in \u003ca href=\"https://github.com/open-webui/open-webui/commits\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=main\u0026new-version=main)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/ArloL/open-webui-runner/pull/8","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArloL%2Fopen-webui-runner/issues/8","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/8/packages"},{"uuid":"2862841201","node_id":"PR_kwDOPIpjyc6qo31x","number":11,"state":"closed","title":"Bump open-webui/open-webui from v0.6.30-slim to 0.6.31-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":0,"pull_request":true,"closed_at":"2025-09-27T18:25:38.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-09-26T07:20:59.000Z","updated_at":"2025-09-27T18:25:38.000Z","time_to_close":126279,"merged_at":"2025-09-27T18:25:38.000Z","merged_by":"rahulsalvi","closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.6.30-slim","new_version":"0.6.31-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.6.30-slim to 0.6.31-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.31\u003c/h2\u003e\n\u003ch2\u003e[0.6.31] - 2025-09-25\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔌 MCP (streamable HTTP) server support was added alongside existing OpenAPI server integration, allowing users to connect both server types through an improved server configuration interface. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15932\"\u003e#15932\u003c/a\u003e \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/16651\"\u003e#16651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/777e81f7a8aca957a359d51df8388e5af4721a68\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/de7f7b3d855641450f8e5aac34fbae0665e0b80e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1bbf3a91e4713039364b790e886e59b401572d0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c55afc42559c32a6f0c8beb0f1bb18e9360ab8af\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/61f20acf61f4fe30c0e5b0180949f6e1a8cf6524\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 To enable MCP server authentication, OAuth 2.1 dynamic client registration was implemented with secure automatic client registration, encrypted session management, and seamless authentication flows. \u003ca href=\"https://github.com/open-webui/open-webui/commit/972be4eda5a394c111e849075f94099c9c0dd9aa\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/77e971dd9fbeee806e2864e686df5ec75e82104b\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/879abd7feea3692a2f157da4a458d30f27217508\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/422d38fd114b1ebd8a7dbb114d64e14791e67d7a\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/709\"\u003e#709\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/709\"\u003eopen-webui/docs#709\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🛠️ External \u0026amp; Built-In Tools can now support rich UI element embedding (\u003ca href=\"https://docs.openwebui.com/features/plugin/tools/development\"\u003eDocs\u003c/a\u003e), allowing tools to return HTML content and interactive iframes that display directly within chat conversations with configurable security settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/07c5b25bc8b63173f406feb3ba183d375fedee6a\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a5d8882bba7933a2c2c31c0a1405aba507c370bb\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/7be5b7f50f498de97359003609fc5993a172f084\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a89ffccd7e96705a4a40e845289f4fcf9c4ae596\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Note editor now supports drag-and-drop reordering of list items with visual drag handles, making list organization more intuitive and efficient. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e4e97e727e9b4971f1c363b1280ca3a101599d88\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/aeb5288a3c7a6e9e0a47b807cc52f870c1b7dbe6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Search modal was enhanced with quick action buttons for starting new conversations and creating notes, with intelligent content pre-population from search queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/aa6f63a335e172fec1dc94b2056541f52c1167a6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/612a52d7bb7dbe9fa0bbbc8ac0a552d2b9801146\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b03529b006f3148e895b1094584e1ab129ecac5b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Tool user valve configuration interface was added to the integrations menu, displaying clickable gear icon buttons with tooltips for tools that support user-specific settings, making personal tool configurations easily accessible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/27d61307cdce97ed11a05ec13fc300249d6022cd\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Channel access control was enhanced to require write permissions for posting, editing, and deleting messages, while read-only users can view content but cannot contribute. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17543\"\u003e#17543\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Channel models now support image processing, allowing AI assistants to view and analyze images shared in conversation threads. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9f0010e234a6f40782a66021435d3c02b9c23639\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🌐 Attach Webpage button was added to the message input menu, providing a user-friendly modal interface for attaching web content and YouTube videos as an alternative to the existing URL syntax. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17534\"\u003e#17534\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Redis session storage support was added for OAuth redirects, providing better state handling in multi-pod Kubernetes deployments and resolving CSRF mismatch errors. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17223\"\u003e#17223\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15373\"\u003e#15373\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Ollama Cloud web search integration was added as a new search engine option, providing access to web search functionality through Ollama's cloud infrastructure. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e06489d92baca095b8f376fbef223298c7772579\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4b6d34438bcfc45463dc7a9cb984794b32c1f0a1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/05c46008da85357dc6890b846789dfaa59f4a520\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fe65fe0b97ec5a8fff71592ff04a25c8e123d108\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/708\"\u003e#708\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/708\"\u003eopen-webui/docs#708\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🔍 Perplexity Websearch API integration was added as a new search engine option, providing access to the new websearch functionality provided by Perplexity. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17756\"\u003e#17756\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/7f411dd5cc1c29733216f79e99eeeed0406a2afe\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ OneDrive integration was improved to support separate client IDs for personal and business authentication, enabling both integrations to work simultaneously. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17619\"\u003e#17619\u003c/a\u003e, \u003ca href=\"https://docs.openwebui.com/tutorials/integrations/onedrive-sharepoint\"\u003eDocs\u003c/a\u003e, \u003ca href=\"https://docs.openwebui.com/getting-started/env-configuration/#onedrive\"\u003eDocs\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Pending user overlay content now supports markdown formatting, enabling rich text display for custom messages similar to banner functionality. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17681\"\u003e#17681\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Image generation model selection was centralized to enable dynamic model override in function calls, allowing pipes and tools to specify different models than the global default while maintaining backward compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17689\"\u003e#17689\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Interface design was modernized with updated visual styling, improved spacing, and refined component layouts across modals, sidebar, settings, and navigation elements. \u003ca href=\"https://github.com/open-webui/open-webui/commit/27a91cc80a24bda0a3a188bc3120a8ab57b00881\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4ad743098615f9c58daa9df392f31109aeceeb16\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Notes query performance was optimized through database-level filtering and separated access control logic, reducing memory usage and eliminating N+1 query problems for better scalability. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17607\"\u003e#17607\u003c/a\u003e \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/da661756fa7eec754270e6dd8c67cbf74a28a17f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Page loading performance was optimized by deferring API requests until components are actually opened, including ChangelogModal, ModelSelector, RecursiveFolder, ArchivedChatsModal, and SearchModal. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17542\"\u003e#17542\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17555\"\u003e#17555\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17557\"\u003e#17557\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17541\"\u003e#17541\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17640\"\u003e#17640\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Bundle size was reduced by 1.58MB through optimized highlight.js language support, improving page loading speed and reducing bandwidth usage. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17645\"\u003e#17645\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Editor collaboration functionality was refactored to reduce package size by 390KB and minimize compilation errors, improving build performance and reliability. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17593\"\u003e#17593\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e♿ Enhanced user interface accessibility through the addition of unique element IDs, improving targeting for testing, styling, and assistive technologies while providing better semantic markup for screen readers and accessibility tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17746\"\u003e#17746\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Chinese (Simplified and Traditional), Korean, Irish, Spanish, Finnish, French, Kabyle, Russian, and Catalan were enhanced and improved.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ SVG content security was enhanced by implementing DOMPurify sanitization to prevent XSS attacks through malicious SVG elements, ensuring safe rendering of user-generated SVG content. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/750a659a9fee7687e667d9d755e17b8a0c77d557\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ OneDrive attachment menu rendering issues were resolved by restructuring the submenu interface from dropdown to tabbed navigation, preventing menu items from being hidden or clipped due to overflow constraints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17554\"\u003e#17554\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/90e4b49b881b644465831cc3028bb44f0f7a2196\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Attached conversation references now persist throughout the entire chat session, ensuring models can continue querying referenced conversations after multiple conversation turns. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17750\"\u003e#17750\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Search modal text box focus issues after pinning or unpinning chats were resolved, allowing users to properly exit the search interface by clicking outside the text box. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17743\"\u003e#17743\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Search function chat list is now properly updated in real-time when chats are created or deleted, eliminating stale search results and preview loading failures. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17741\"\u003e#17741\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Chat jitter and delayed code block expansion in multi-model sessions were resolved by reverting dynamic CodeEditor loading, restoring stable rendering behavior. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17715\"\u003e#17715\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17684\"\u003e#17684\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📎 File upload handling was improved to properly recognize uploaded files even when no accompanying text message is provided, resolving issues where attachments were ignored in custom prompts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17492\"\u003e#17492\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Chat conversation referencing within projects was restored by including foldered chats in the reference menu, allowing users to properly quote conversations from within their project scope. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17530\"\u003e#17530\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 RAG query generation is now skipped when all attached files are set to full context mode, preventing unnecessary retrieval operations and improving system efficiency. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17744\"\u003e#17744\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 Memory leaks in file handling and HTTP connections are prevented through proper resource cleanup, ensuring stable memory usage during large file downloads and processing operations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17608\"\u003e#17608\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 OAuth access token refresh errors are resolved by properly implementing async/await patterns, preventing \u0026quot;coroutine object has no attribute get\u0026quot; failures during token expiry. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17585\"\u003e#17585\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17678\"\u003e#17678\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ Valve behavior was improved to properly handle default values and array types, ensuring only explicitly set values are persisted while maintaining consistent distinction between custom and default valve states. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17664\"\u003e#17664\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Hybrid search functionality was enhanced to handle inconsistent parameter types and prevent failures when collection results are None, empty, or in unexpected formats. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17617\"\u003e#17617\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 Empty folder deletion is now allowed regardless of chat deletion permission restrictions, resolving cases where users couldn't remove folders after deleting all contained chats. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17683\"\u003e#17683\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Rich text editor console errors were resolved by adding proper error handling when the TipTap editor view is not available or not yet mounted. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17697\"\u003e#17697\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗒️ Hidden models are now properly excluded from the notes section dropdown and default model selection, preventing users from accessing models they shouldn't see. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17722\"\u003e#17722\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ AI-generated image download filenames now use a clean, translatable \u0026quot;Generated Image\u0026quot; format instead of potentially problematic response text, improving file management and compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17721\"\u003e#17721\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Toggle switch display issues in the Integrations interface are fixed, preventing background highlighting and obscuring on hover. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17564\"\u003e#17564\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/598282cf75de358215d045c617e70d28bc48929e\"\u003e\u003ccode\u003e598282c\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17747\"\u003e#17747\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f7ea60b500b589ca95f32d5e6997481f796786a4\"\u003e\u003ccode\u003ef7ea60b\u003c/code\u003e\u003c/a\u003e Update CHANGELOG.md\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2fa222d00a8120e5813b2efb2f2089f6c1fbde49\"\u003e\u003ccode\u003e2fa222d\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/6920fed97e805224e94c6ecdeb80bc91efebfb76\"\u003e\u003ccode\u003e6920fed\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/528e58155b5cb4f55e138efb8d153881c667d1c5\"\u003e\u003ccode\u003e528e581\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/503fc354cc70d56888057f629fff6ee9d6c7de19\"\u003e\u003ccode\u003e503fc35\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17752\"\u003e#17752\u003c/a\u003e from Classic298/changelog-done\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4eec423950e722df6fdfb5145fb101e64225a0e0\"\u003e\u003ccode\u003e4eec423\u003c/code\u003e\u003c/a\u003e Update CHANGELOG.md\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/52bc5306b02002d66fc4066277b74dc799379b0f\"\u003e\u003ccode\u003e52bc530\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/90e4b49b881b644465831cc3028bb44f0f7a2196\"\u003e\u003ccode\u003e90e4b49\u003c/code\u003e\u003c/a\u003e refac/fix: onedrive input menu styling issue\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/750a659a9fee7687e667d9d755e17b8a0c77d557\"\u003e\u003ccode\u003e750a659\u003c/code\u003e\u003c/a\u003e security: svg xss fix\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.30...v0.6.31\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.6.30-slim\u0026new-version=0.6.31-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/11","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/11","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/11/packages"},{"uuid":"2817956206","node_id":"PR_kwDOPIpjyc6n9plu","number":9,"state":"closed","title":"Bump open-webui/open-webui from 0.6.26-slim to v0.6.28-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":"2025-09-14T22:42:09.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-09-11T07:23:36.000Z","updated_at":"2025-09-14T22:42:09.000Z","time_to_close":314313,"merged_at":"2025-09-14T22:42:09.000Z","merged_by":"rahulsalvi","closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.26-slim","new_version":"v0.6.28-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.26-slim to v0.6.28-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.28\u003c/h2\u003e\n\u003ch2\u003e[0.6.28] - 2025-09-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔍 The \u0026quot;@\u0026quot; command for model selection now supports real-time search and filtering, improving usability and aligning its behavior with other input commands. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17307\"\u003e#17307\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f2a09c71499489ee71599af4a179e7518aaf658b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ External tool server data handling is now more robust, automatically attempting to parse specifications as JSON before falling back to YAML, regardless of the URL extension. \u003ca href=\"https://github.com/open-webui/open-webui/commit/774c0056bde88ed4831422efa81506488e3d6641\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 The \u0026quot;Title\u0026quot; field is now automatically focused when creating a new chat folder, streamlining the folder creation process. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17315\"\u003e#17315\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c51a651a2d5e2a27546416666812e9b92205562d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Brazilian Portuguese and Simplified Chinese translations were expanded and refined.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔊 A regression affecting Text-to-Speech for local providers using the OpenAI engine was fixed by reverting a URL joining change. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17316\"\u003e#17316\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8339f59cdfc63f2d58c8e26933d1bf1438479d75\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🪧 A regression was fixed where the input modal for prompts with placeholders would not open, causing the raw prompt text to be pasted into the chat input field instead. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17325\"\u003e#17325\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/d5cb65527eaa4831459a4c7dbf187daa9c0525ae\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 An issue was resolved where modified connection keys in the OpenAIConnection component did not take effect. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17324\"\u003e#17324\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.27\u003c/h2\u003e\n\u003ch2\u003e[0.6.27] - 2025-09-09\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📁 Emoji folder icons were added, allowing users to personalize workspace organization with visual cues, including improved chevron display. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1588f42fe777ad5d807e3f2fc8dbbc47a8db87c0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b70c0f36c0f5bbfc2a767429984d6fba1a7bb26c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/11dea8795bfce42aa5d8d58ef316ded05173bd87\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c0a47169fa059154d5f5a9ea6b94f9a66d82f255\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 The 'Search Collection' input field now dynamically displays the total number of files within the knowledge base. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/fbbe1117ae4c9c8fec6499d790eee275818eccc5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ A provider toggle in connection settings now allows users to manually specify Azure OpenAI deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/5bdd334b74fbd154085f2d590f4afdba32469c8a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Model list caching performance was optimized by fixing cache key generation to reduce redundant API calls. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17158\"\u003e#17158\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Azure OpenAI image generation is now supported, with configurations for IMAGES_OPENAI_API_VERSION via environment variable and admin UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17147\"\u003e#17147\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/16274\"\u003e#16274\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/679\"\u003e#679\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/679\"\u003eopen-webui/docs#679\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e⚡ Comprehensive N+1 query performance is optimized by reducing database queries from 1+N to 1+1 patterns across major listing endpoints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17165\"\u003e#17165\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17160\"\u003e#17160\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17161\"\u003e#17161\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17162\"\u003e#17162\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17159\"\u003e#17159\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17166\"\u003e#17166\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The PDF.js library is now dynamically loaded, significantly reducing initial page load size and improving responsiveness. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17222\"\u003e#17222\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The heic2any library is now dynamically loaded across various message input components, including channels, for faster page loads. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17225\"\u003e#17225\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17229\"\u003e#17229\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📚 The knowledge API now supports a \u0026quot;delete_file\u0026quot; query parameter, allowing configurable file deletion behavior. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/22c4ef4fb096498066b73befe993ae3a82f7a8e7\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Llama.cpp timing statistics are now integrated into the usage field for comprehensive model performance metrics. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/e830b4959ecd4b2795e29e53026984a58a7696a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ The PGVECTOR_CREATE_EXTENSION environment variable now allows control over automatic pgvector extension creation. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c2b4976c82d335ed524bd80dc914b5e2f5bfbd9e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b45219c8b15b48d5ee3d42983e1107bbcefbab01\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/672\"\u003e#672\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/672\"\u003eopen-webui/docs#672\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🔒 Comprehensive server-side OAuth token management was implemented, securely storing encrypted tokens in a new database table and introducing an automatic refresh mechanism, enabling seamless and secure forwarding of valid user-specific OAuth tokens to downstream services, including OpenAI-compatible endpoints and external tool servers via the new \u0026quot;system_oauth\u0026quot; authentication type, resolving long-standing issues such as large token size limitations, stale/expired tokens, and reliable token propagation, and enhancing overall security by minimizing client-side token exposure, configurable via \u0026quot;ENABLE_OAUTH_ID_TOKEN_COOKIE\u0026quot; and \u0026quot;OAUTH_SESSION_TOKEN_ENCRYPTION_KEY\u0026quot; environment variables. [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/683\"\u003e#683\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/683\"\u003eopen-webui/docs#683\u003c/a\u003e), \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17210\"\u003e#17210\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/8957\"\u003e#8957\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/11029\"\u003e#11029\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17178\"\u003e#17178\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17183\"\u003e#17183\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/217f4daef09b36d3d4cc4681e11d3ebd9984a1a5\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fc11e4384fe98fac659e10596f67c23483578867\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f11bdc6ab5dd5682bb3e27166e77581f5b8af3e0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f71834720e623761d972d4d740e9bbd90a3a86c6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b5bb6ae177dcdc4e8274d7e5ffa50bc8099fd466\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b786d1e3f3308ef4f0f95d7130ddbcaaca4fc927\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8a9f8627017bd0a74cbd647891552b26e56aabb7\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/30d1dc2c60e303756120fe1c5538968c4e6139f4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/2b2d123531eb3f42c0e940593832a64e2806240d\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/6f6412dd16c63c2bb4df79a96b814bf69cb3f880\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Conditional Permission Hardening for OpenShift Deployments: Added a build argument to enable optional permission hardening for OpenShift and container environments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0ebe4f8f8490451ac8e85a4846f010854d9b54e5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Regex pattern support is added for OAuth blocked groups, allowing more flexible group filtering rules. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/df66e21472646648d008ebb22b0e8d5424d491df\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Web search result display was enhanced to include titles and favicons, providing a clearer overview of search sources. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/33f04a771455e3fabf8f0e8ebb994ae7f41b8ed4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0a85dd4bca23022729eafdbc82c8c139fa365af2\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/16090bc2721fde492afa2c4af5927e2b668527e1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17197\"\u003e#17197\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14179\"\u003e#14179\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1cdb7aed1ee9bf81f2fd0404be52dcfa64f8ed4f\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/f2525ebc447c008cf7269ef20ce04fa456f302c4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/7f523de408ede4075349d8de71ae0214b7e1a62e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/3d37e4a42d344051ae715ab59bd7b5718e46c343\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/cd5e2be27b613314aadda6107089331783987985\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/6dc0df247347aede2762fe2065cf30275fd137ae\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 A new setting was added to control whether clicking a suggested prompt automatically sends the message or only inserts the text. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17192\"\u003e#17192\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e023a98f11fc52feb21e4065ec707cc98e50c7d3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, Catalan, and Spanish were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔍 Hybrid search functionality now correctly handles lexical-semantic weight labels and avoids errors when BM25 weight is zero. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17049\"\u003e#17049\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17046\"\u003e#17046\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛑 Task stopping errors are prevented by gracefully handling multiple stop requests for the same task. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17195\"\u003e#17195\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐍 Code execution package detection precision is improved in Pyodide to prevent unnecessary package inclusions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/bbe116795860a81a647d9567e0d9cb1950650095\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Tool message format API compliance is fixed by ensuring content fields in tool call responses contain valid string values instead of null. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/37bf0087e5b8a324009c9d06b304027df351ea6b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📱 Mobile app config API authentication now supports Authorization header token verification with cookie fallback for iOS and Android requests. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17175\"\u003e#17175\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 Knowledge file save race conditions are prevented by serializing API calls and adding an \u0026quot;isSaving\u0026quot; guard. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17137\"\u003e#17137\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/4ca936f0bf9813bee11ec8aea41d7e34fb6b16a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 The SSO login button visibility is restored for OIDC PKCE authentication without a client secret. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17012\"\u003e#17012\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/171021cfa4276f63fd9fd7f31fa0c904fb13c24c\"\u003e\u003ccode\u003e171021c\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17327\"\u003e#17327\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d3d7b209b2aa156eadd65f69d79984c205f58aee\"\u003e\u003ccode\u003ed3d7b20\u003c/code\u003e\u003c/a\u003e refac: changelog styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/6ddbb41aac69bcee68bf72566c338aa56cdbd1ca\"\u003e\u003ccode\u003e6ddbb41\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17333\"\u003e#17333\u003c/a\u003e from Classic298/patch-2\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2a9925fe18dc3e022ff662918965dd3ac1c52da0\"\u003e\u003ccode\u003e2a9925f\u003c/code\u003e\u003c/a\u003e Update CHANGELOG.md\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/81e401a520179484cffa2ace80c25955b08de7d3\"\u003e\u003ccode\u003e81e401a\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ba432090c5261bc4f193c9eb8bb84be0ad269bd6\"\u003e\u003ccode\u003eba43209\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17320\"\u003e#17320\u003c/a\u003e from ShirasawaSama/patch-16\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/de634a7599f6340db55137213d0eba7c481228ca\"\u003e\u003ccode\u003ede634a7\u003c/code\u003e\u003c/a\u003e chore: dep bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/803daebfe4f2986d741a9654725c3371e23ef71d\"\u003e\u003ccode\u003e803daeb\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/958a76d448b69a8e7720ae1743246ca3c545ee0b\"\u003e\u003ccode\u003e958a76d\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2dd0eaad738a77b70051c690402891e12251261b\"\u003e\u003ccode\u003e2dd0eaa\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17328\"\u003e#17328\u003c/a\u003e from open-webui/main\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.26...v0.6.28\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.26-slim\u0026new-version=v0.6.28-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/9","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/9","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/9/packages"},{"uuid":"2814456821","node_id":"PR_kwDOPIpjyc6nwTP1","number":8,"state":"open","title":"Bump open-webui/open-webui from 0.6.26-slim to v0.6.27-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-09-10T07:23:04.000Z","updated_at":"2025-09-10T07:23:05.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.26-slim","new_version":"v0.6.27-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.26-slim to v0.6.27-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.27\u003c/h2\u003e\n\u003ch2\u003e[0.6.27] - 2025-09-09\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📁 Emoji folder icons were added, allowing users to personalize workspace organization with visual cues, including improved chevron display. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1588f42fe777ad5d807e3f2fc8dbbc47a8db87c0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b70c0f36c0f5bbfc2a767429984d6fba1a7bb26c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/11dea8795bfce42aa5d8d58ef316ded05173bd87\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c0a47169fa059154d5f5a9ea6b94f9a66d82f255\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 The 'Search Collection' input field now dynamically displays the total number of files within the knowledge base. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/fbbe1117ae4c9c8fec6499d790eee275818eccc5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ A provider toggle in connection settings now allows users to manually specify Azure OpenAI deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/5bdd334b74fbd154085f2d590f4afdba32469c8a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Model list caching performance was optimized by fixing cache key generation to reduce redundant API calls. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17158\"\u003e#17158\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Azure OpenAI image generation is now supported, with configurations for IMAGES_OPENAI_API_VERSION via environment variable and admin UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17147\"\u003e#17147\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/16274\"\u003e#16274\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/679\"\u003e#679\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/679\"\u003eopen-webui/docs#679\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e⚡ Comprehensive N+1 query performance is optimized by reducing database queries from 1+N to 1+1 patterns across major listing endpoints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17165\"\u003e#17165\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17160\"\u003e#17160\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17161\"\u003e#17161\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17162\"\u003e#17162\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17159\"\u003e#17159\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17166\"\u003e#17166\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The PDF.js library is now dynamically loaded, significantly reducing initial page load size and improving responsiveness. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17222\"\u003e#17222\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The heic2any library is now dynamically loaded across various message input components, including channels, for faster page loads. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17225\"\u003e#17225\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17229\"\u003e#17229\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📚 The knowledge API now supports a \u0026quot;delete_file\u0026quot; query parameter, allowing configurable file deletion behavior. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/22c4ef4fb096498066b73befe993ae3a82f7a8e7\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Llama.cpp timing statistics are now integrated into the usage field for comprehensive model performance metrics. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/e830b4959ecd4b2795e29e53026984a58a7696a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ The PGVECTOR_CREATE_EXTENSION environment variable now allows control over automatic pgvector extension creation. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c2b4976c82d335ed524bd80dc914b5e2f5bfbd9e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b45219c8b15b48d5ee3d42983e1107bbcefbab01\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/672\"\u003e#672\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/672\"\u003eopen-webui/docs#672\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🔒 Comprehensive server-side OAuth token management was implemented, securely storing encrypted tokens in a new database table and introducing an automatic refresh mechanism, enabling seamless and secure forwarding of valid user-specific OAuth tokens to downstream services, including OpenAI-compatible endpoints and external tool servers via the new \u0026quot;system_oauth\u0026quot; authentication type, resolving long-standing issues such as large token size limitations, stale/expired tokens, and reliable token propagation, and enhancing overall security by minimizing client-side token exposure, configurable via \u0026quot;ENABLE_OAUTH_ID_TOKEN_COOKIE\u0026quot; and \u0026quot;OAUTH_SESSION_TOKEN_ENCRYPTION_KEY\u0026quot; environment variables. [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/683\"\u003e#683\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/683\"\u003eopen-webui/docs#683\u003c/a\u003e), \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17210\"\u003e#17210\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/8957\"\u003e#8957\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/11029\"\u003e#11029\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17178\"\u003e#17178\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17183\"\u003e#17183\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/217f4daef09b36d3d4cc4681e11d3ebd9984a1a5\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fc11e4384fe98fac659e10596f67c23483578867\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f11bdc6ab5dd5682bb3e27166e77581f5b8af3e0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f71834720e623761d972d4d740e9bbd90a3a86c6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b5bb6ae177dcdc4e8274d7e5ffa50bc8099fd466\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b786d1e3f3308ef4f0f95d7130ddbcaaca4fc927\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8a9f8627017bd0a74cbd647891552b26e56aabb7\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/30d1dc2c60e303756120fe1c5538968c4e6139f4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/2b2d123531eb3f42c0e940593832a64e2806240d\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/6f6412dd16c63c2bb4df79a96b814bf69cb3f880\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Conditional Permission Hardening for OpenShift Deployments: Added a build argument to enable optional permission hardening for OpenShift and container environments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0ebe4f8f8490451ac8e85a4846f010854d9b54e5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Regex pattern support is added for OAuth blocked groups, allowing more flexible group filtering rules. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/df66e21472646648d008ebb22b0e8d5424d491df\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Web search result display was enhanced to include titles and favicons, providing a clearer overview of search sources. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/33f04a771455e3fabf8f0e8ebb994ae7f41b8ed4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0a85dd4bca23022729eafdbc82c8c139fa365af2\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/16090bc2721fde492afa2c4af5927e2b668527e1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17197\"\u003e#17197\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14179\"\u003e#14179\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1cdb7aed1ee9bf81f2fd0404be52dcfa64f8ed4f\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/f2525ebc447c008cf7269ef20ce04fa456f302c4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/7f523de408ede4075349d8de71ae0214b7e1a62e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/3d37e4a42d344051ae715ab59bd7b5718e46c343\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/cd5e2be27b613314aadda6107089331783987985\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/6dc0df247347aede2762fe2065cf30275fd137ae\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 A new setting was added to control whether clicking a suggested prompt automatically sends the message or only inserts the text. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17192\"\u003e#17192\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e023a98f11fc52feb21e4065ec707cc98e50c7d3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, Catalan, and Spanish were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔍 Hybrid search functionality now correctly handles lexical-semantic weight labels and avoids errors when BM25 weight is zero. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17049\"\u003e#17049\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17046\"\u003e#17046\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛑 Task stopping errors are prevented by gracefully handling multiple stop requests for the same task. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17195\"\u003e#17195\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐍 Code execution package detection precision is improved in Pyodide to prevent unnecessary package inclusions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/bbe116795860a81a647d9567e0d9cb1950650095\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Tool message format API compliance is fixed by ensuring content fields in tool call responses contain valid string values instead of null. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/37bf0087e5b8a324009c9d06b304027df351ea6b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📱 Mobile app config API authentication now supports Authorization header token verification with cookie fallback for iOS and Android requests. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17175\"\u003e#17175\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 Knowledge file save race conditions are prevented by serializing API calls and adding an \u0026quot;isSaving\u0026quot; guard. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17137\"\u003e#17137\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/4ca936f0bf9813bee11ec8aea41d7e34fb6b16a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 The SSO login button visibility is restored for OIDC PKCE authentication without a client secret. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17012\"\u003e#17012\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔊 Text-to-Speech (TTS) API requests now use proper URL joining methods, ensuring reliable functionality regardless of trailing slashes in the base URL. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17061\"\u003e#17061\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛡️ Admin account creation on Hugging Face Spaces now correctly detects the configured port, resolving issues with custom port deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17064\"\u003e#17064\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 Unicode filename support is improved for external document loaders by properly URL-encoding filenames in HTTP headers. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17013\"\u003e#17013\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17000\"\u003e#17000\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 Web page and YouTube attachments are now correctly processed by setting their type as \u0026quot;text\u0026quot; and using collection names for accurate content retrieval. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/487979859a6ffcfd60468f523822cdf838fbef5b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✍️ Message input composition event handling is fixed to properly manage text input for multilingual users using Input Method Editors (IME). \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17085\"\u003e#17085\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Follow-up tooltip duplication is removed, streamlining the user interface and preventing visual clutter. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17186\"\u003e#17186\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Chat button text display is corrected by preventing clipping of descending characters and removing unnecessary capitalization. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17191\"\u003e#17191\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧠 RAG Loop/Error with Gemma 3.1 2B Instruct is fixed by correctly unwrapping unexpected single-item list responses from models. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1bc9711afd2b72cd07c4e539a83783868733767c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17213\"\u003e#17213\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ HEIC conversion failures are resolved, improving robustness of image handling. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17225\"\u003e#17225\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 The slim Docker image size regression has been fixed by refining the build process to correctly exclude components when USE_SLIM=true. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16997\"\u003e#16997\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/be373e9fd42ac73b0302bdb487e16dbeae178b4e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/0ebe4f8f8490451ac8e85a4846f010854d9b54e5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 Knowledge base update validation errors are resolved, ensuring seamless management via UI or API. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17244\"\u003e#17244\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/9aac1489080a5c9441e89b1a56de0d3a672bc5fb\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Resolved a security issue where a global web search setting overrode model-specific restrictions, ensuring model-level settings are now correctly prioritized. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17151\"\u003e#17151\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/9368d0ac751ec3072d5a96712b80a9b20a642ce6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 OAuth redirect reliability is improved by robustly preserving the intended redirect path using session storage. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17235\"\u003e#17235\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/4f2b821088367da18374027919594365c7a3f459\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/15575\"\u003e#15575\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/d9f97c832c556fae4b116759da0177bf4fe619de\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Fixed a security vulnerability where knowledge base access within chat folders persisted after permissions were revoked. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17182\"\u003e#17182\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/40e40d1dddf9ca937e99af41c8ca038dbc93a7e6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 OIDC access denied errors are now displayed as user-friendly toast notifications instead of raw JSON. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17208\"\u003e#17208\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/3d6d050ad82d360adc42d6e9f42e8faf8d13c9f4\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Chat exception handling is enhanced to prevent system instability during message generation and ensure graceful error recovery. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/f56889c5c7f0cf1a501c05d35dfa614e4f8b6958\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Static asset authentication is improved by adding crossorigin=\u0026quot;use-credentials\u0026quot; attributes to all link elements, enabling proper cookie forwarding for proxy environments and authenticated requests to favicon, manifest, and stylesheet resources. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17280\"\u003e#17280\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f17d8b5d19e1a05df7d63f53e939c99772a59c1e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/918f507d8cdc652ae913b8596877a8a50b845114\"\u003e\u003ccode\u003e918f507\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17070\"\u003e#17070\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f7e85cd0bfa4efc66cbe7e7ec19deecc981c203f\"\u003e\u003ccode\u003ef7e85cd\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4b4583df6280437ff208905d7dcc0c96d979f090\"\u003e\u003ccode\u003e4b4583d\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/bcf76dfa74b98b82fd4a2c9a47292b174b1a84c0\"\u003e\u003ccode\u003ebcf76df\u003c/code\u003e\u003c/a\u003e refac: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/485392fe63fe488100dc2c1086cdd9b4980362e2\"\u003e\u003ccode\u003e485392f\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/cbb4684b169fc89bb30a60b199158a6a6a170957\"\u003e\u003ccode\u003ecbb4684\u003c/code\u003e\u003c/a\u003e chore\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0531ca6530d1f63dcf348e65bb0367de93499898\"\u003e\u003ccode\u003e0531ca6\u003c/code\u003e\u003c/a\u003e refac/fix\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/32cb9df3c49155f2e625672a806f1afe7fa1e3fb\"\u003e\u003ccode\u003e32cb9df\u003c/code\u003e\u003c/a\u003e refac/enh: knowledge ac backend validation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/71fd483fba2d8828cdc46298ce702d77d16d7203\"\u003e\u003ccode\u003e71fd483\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17276\"\u003e#17276\u003c/a\u003e from Elettrotecnica/extend-docling-configuration\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/63f38c584f8e5297490dd446364712fa17f7e869\"\u003e\u003ccode\u003e63f38c5\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.26...v0.6.27\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.26-slim\u0026new-version=v0.6.27-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/8","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/8","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/8/packages"},{"uuid":"3351926904","node_id":"PR_kwDOPIpjyc6lN-Ea","number":6,"state":"open","title":"Bump open-webui/open-webui from 0.6.22 to 0.6.25","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-08-25T13:44:21.000Z","updated_at":"2025-08-28T17:21:22.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.22","new_version":"0.6.25","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.22 to 0.6.25.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.25\u003c/h2\u003e\n\u003ch2\u003e[0.6.25] - 2025-08-22\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Generation Reliability Restored\u003c/strong\u003e: Fixed a key issue causing image generation failures.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eReranking Functionality Restored\u003c/strong\u003e: Resolved errors with rerank feature.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.24\u003c/h2\u003e\n\u003ch2\u003e[0.6.24] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e♿ \u003cstrong\u003eHigh Contrast Mode in Chat Messages\u003c/strong\u003e: Implemented enhanced High Contrast Mode support for chat messages, making text and important details easier to read and improving accessibility for users with visual preferences or requirements.\u003c/li\u003e\n\u003cli\u003e🌎 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Enhanced and expanded translations for a more natural and professional user experience for speakers of these languages across the entire interface.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eComfyUI Image Generation Restored\u003c/strong\u003e: Fixed a critical bug where ComfyUI-based image generation was not functioning, ensuring users can once again effortlessly create and interact with AI-generated visuals in their workflows.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTool Server Loading and Visibility Restored\u003c/strong\u003e: Resolved an issue where connected tool servers were not loading or visible, restoring seamless integration and uninterrupted access to all external and custom tools directly within the platform.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis User Session Reliability\u003c/strong\u003e: Fixed a problem affecting the saving of user sessions in Redis, ensuring reliable login sessions, stable authentication, and secure multi-user environments.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.23\u003c/h2\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.25] - 2025-08-22\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Generation Reliability Restored\u003c/strong\u003e: Fixed a key issue causing image generation failures.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eReranking Functionality Restored\u003c/strong\u003e: Resolved errors with rerank feature.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.24] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e♿ \u003cstrong\u003eHigh Contrast Mode in Chat Messages\u003c/strong\u003e: Implemented enhanced High Contrast Mode support for chat messages, making text and important details easier to read and improving accessibility for users with visual preferences or requirements.\u003c/li\u003e\n\u003cli\u003e🌎 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Enhanced and expanded translations for a more natural and professional user experience for speakers of these languages across the entire interface.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eComfyUI Image Generation Restored\u003c/strong\u003e: Fixed a critical bug where ComfyUI-based image generation was not functioning, ensuring users can once again effortlessly create and interact with AI-generated visuals in their workflows.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTool Server Loading and Visibility Restored\u003c/strong\u003e: Resolved an issue where connected tool servers were not loading or visible, restoring seamless integration and uninterrupted access to all external and custom tools directly within the platform.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis User Session Reliability\u003c/strong\u003e: Fixed a problem affecting the saving of user sessions in Redis, ensuring reliable login sessions, stable authentication, and secure multi-user environments.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eResolved Critical OIDC SSO Login Failure\u003c/strong\u003e: Fixed a critical issue where OIDC Single Sign-On (SSO) logins failed due to an error in setting the authentication token as a cookie during the redirect process. This ensures reliable and seamless authentication for users utilizing OIDC providers, restoring full login functionality that was impacted by previous security hardening.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePrevented UI Blocking by Unreachable Webhooks\u003c/strong\u003e: Resolved a critical performance and user experience issue where synchronous webhook calls to unreachable or slow endpoints would block the entire user interface for all users. Webhook requests are now processed asynchronously using \u0026quot;aiohttp\u0026quot;, ensuring that the UI remains responsive and functional even if webhook delivery encounters delays or failures.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1db8dec4f52fc0fa8f8f7bfbb8ea5bde41fee17d\"\u003e\u003ccode\u003e1db8dec\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16821\"\u003e#16821\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/dafedf567561fdeb2f3010900cf99846820a3c69\"\u003e\u003ccode\u003edafedf5\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/37a3de0703c472db42633d6007a19a428c7e4e67\"\u003e\u003ccode\u003e37a3de0\u003c/code\u003e\u003c/a\u003e fix\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/72b25ab78bb00424e027d17427ec0c7fd78b4ed0\"\u003e\u003ccode\u003e72b25ab\u003c/code\u003e\u003c/a\u003e fix: image generation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/fbff4e19de591a440fcc5716e6796a6ed2d512b7\"\u003e\u003ccode\u003efbff4e1\u003c/code\u003e\u003c/a\u003e fix: reranking\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2777bab1485aad097aa41c44a76f49be141eb061\"\u003e\u003ccode\u003e2777bab\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16810\"\u003e#16810\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4ec70e3d46ecf7b6453b0f93161203ff678fea3e\"\u003e\u003ccode\u003e4ec70e3\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/43b2eca4182df4d416665932b8320a18f9dbd09a\"\u003e\u003ccode\u003e43b2eca\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/99f7d1b62b2f1f8e862402495056b88baba88136\"\u003e\u003ccode\u003e99f7d1b\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/62a5db7719cfd2891e3cb5d4997b60c2e0f3c0eb\"\u003e\u003ccode\u003e62a5db7\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.22...v0.6.25\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.22\u0026new-version=0.6.25)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/6","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/6","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/6/packages"},{"uuid":"2765535190","node_id":"PR_kwDOPIpjyc6k1rfW","number":5,"state":"closed","title":"Bump open-webui/open-webui from 0.6.22 to v0.6.23","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-08-25T13:44:23.000Z","author_association":"NONE","state_reason":null,"created_at":"2025-08-22T08:12:11.000Z","updated_at":"2025-08-25T13:44:23.000Z","time_to_close":279132,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.22","new_version":"v0.6.23","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.22 to v0.6.23.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.23\u003c/h2\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eResolved Critical OIDC SSO Login Failure\u003c/strong\u003e: Fixed a critical issue where OIDC Single Sign-On (SSO) logins failed due to an error in setting the authentication token as a cookie during the redirect process. This ensures reliable and seamless authentication for users utilizing OIDC providers, restoring full login functionality that was impacted by previous security hardening.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePrevented UI Blocking by Unreachable Webhooks\u003c/strong\u003e: Resolved a critical performance and user experience issue where synchronous webhook calls to unreachable or slow endpoints would block the entire user interface for all users. Webhook requests are now processed asynchronously using \u0026quot;aiohttp\u0026quot;, ensuring that the UI remains responsive and functional even if webhook delivery encounters delays or failures.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003ePassword Change Option Hidden for Externally Authenticated Users\u003c/strong\u003e: Resolved an issue where the password change dialog was visible to users authenticated via external methods (e.g., LDAP, OIDC, Trusted Header). The option to change a password in user settings is now correctly hidden for these users, as their passwords are managed externally, streamlining the user interface and preventing confusion.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Temporary Chat and Permission Enforcement Issues\u003c/strong\u003e: Fixed a bug where temporary chats (identified by \u0026quot;chat_id = local\u0026quot;) incorrectly triggered database checks, leading to 404 errors. This also resolves the issue where the 'USER_PERMISSIONS_CHAT_TEMPORARY_ENFORCED' setting was not functioning as intended, ensuring temporary chat mode now works correctly for user roles.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eAdmin Model Visibility for Administrators\u003c/strong\u003e: Private models remained visible and usable for administrators in the chat model selector, even when the intended privacy setting (\u0026quot;ENABLE_ADMIN_WORKSPACE_CONTENT_ACCESS\u0026quot; - now renamed to \u0026quot;BYPASS_ADMIN_ACCESS_CONTROL\u0026quot;) was disabled. This ensures consistent enforcement of model access controls and adherence to the principle of least privilege.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eClarified Web Search Engine Label for DDGS\u003c/strong\u003e: Addressed user confusion and inaccurate labeling by renaming \u0026quot;duckduckgo\u0026quot; to \u0026quot;DDGS\u0026quot; (Dux Distributed Global Search) in the web search engine selector. This clarifies that the system utilizes DDGS, a metasearch library that aggregates results from various search providers, accurately reflecting its underlying functionality rather than implying exclusive use of DuckDuckGo's search engine.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Settings UI Reactivity and Visibility\u003c/strong\u003e: Resolved an issue where settings tabs for 'Connections' and 'Tools' did not dynamically update their visibility based on global administrative feature flags (e.g., 'enable_direct_connections'). The UI now reactively shows or hides these sections, ensuring a consistent and clear experience when administrators control feature availability.\u003c/li\u003e\n\u003cli\u003e🎚️ \u003cstrong\u003eRestored Model and Banner Reordering Functionality\u003c/strong\u003e: Fixed a bug that prevented administrators from reordering models in the Admin Panel's 'Models' settings and banners in the 'Interface' settings via drag-and-drop. The sortable functionality has been restored, allowing for proper customization of display order.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eRestored Custom Pending User Overlay Visibility\u003c/strong\u003e: Fixed an issue where the custom title and description configured for pending users were not visible. The application now correctly exposes these UI configuration settings to pending users, ensuring that the custom onboarding messages are displayed as intended.\u003c/li\u003e\n\u003cli\u003e📥 \u003cstrong\u003eFixed Community Function Import Compatibility\u003c/strong\u003e: Resolved an issue that prevented the successful import of function files downloaded from openwebui.com due to schema differences. The system now correctly processes these files, allowing for seamless integration of community-contributed functions.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eFixed Stale Ollama Version in Docker Images\u003c/strong\u003e: Resolved an issue where the Ollama installation within Docker images could become stale due to caching during the build process. The Dockerfile now includes a mechanism to invalidate the build cache for the Ollama installation step, ensuring that the latest version of Ollama is always installed.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eImproved Milvus Query Handling for Large Datasets\u003c/strong\u003e: Fixed a \u0026quot;MilvusException\u0026quot; that occurred when attempting to query more than 16384 entries from a Milvus collection. The query logic has been refactored to use \u0026quot;query_iterator()\u0026quot;, enabling efficient fetching of larger result sets in batches and resolving the previous limitation on the number of entries that could be retrieved.\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eRestored Message Toolbar Icons for Empty Messages with Files\u003c/strong\u003e: Fixed an issue where the edit, copy, and delete icons were not displayed on user messages that contained an attached file but no text content. This ensures full interaction capabilities for all message types, allowing users to manage their messages consistently.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Streaming Interruption for Kimi-Dev Models\u003c/strong\u003e: Fixed an issue where streaming responses from Kimi-Dev models would halt prematurely upon encountering specific 'thinking' tokens (◁think▷, ◁/think▷). The system now correctly processes these tokens, ensuring uninterrupted streaming and proper handling of hidden or collapsible thinking sections.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eEnhanced Knowledge Base Search Functionality\u003c/strong\u003e: Improved the search capability within the 'Knowledge' section of the Workspace. Previously, searching for knowledge bases required exact term matches or starting with the first letter. Now, the search algorithm has been refined to allow broader, less exact matches, making it easier and more intuitive to find relevant knowledge bases.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eResolved Chinese Input 'Enter' Key Issue (macOS \u0026amp; iOS Safari)\u003c/strong\u003e: Fixed a bug where pressing the 'Enter' key during text composition with Input Method Editors (IMEs) on macOS and iOS Safari browsers would prematurely send the message. The system now robustly handles the composition state by addressing a 'compositionend' event bug specific to Safari, ensuring a smooth and expected typing experience for users of various languages, including Chinese and Korean.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eResolved OAUTH_GROUPS_CLAIM Configuration Issue\u003c/strong\u003e: Fixed a bug where the \u0026quot;OAUTH_GROUPS_CLAIM\u0026quot; environment variable was not correctly parsed due to a typo in the configuration file. This ensures that OAuth group management features, including automatic group creation, now correctly utilize the specified claim from the identity provider, allowing for seamless integration with external user directories like Keycloak.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eResolved Azure PostgreSQL pgvector Extension Permissions\u003c/strong\u003e: Fixed an issue preventing the creation of \u0026quot;pgvector\u0026quot; and \u0026quot;pgcrypto\u0026quot; extensions on Azure PostgreSQL Flexible Servers due to permission limitations (e.g., 'Only members of \u0026quot;azure_pg_admin\u0026quot; are allowed to use \u0026quot;CREATE EXTENSION\u0026quot;'). The extension creation process now includes a conditional check, ensuring seamless deployment and compatibility with Azure PostgreSQL environments even with restricted database user permissions.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Backend Path Resolution and Alembic Stability\u003c/strong\u003e: Fixed issues causing Alembic database migrations to fail due to incorrect path resolution within the application. By implementing canonical path resolution for core directories and refining Alembic configuration, the robustness and correctness of internal pathing have been significantly enhanced, ensuring reliable database operations.\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eResolved Arena Model Identification in Feedback History\u003c/strong\u003e: Fixed an issue where the model used for feedback in arena settings was incorrectly reported as 'arena-model' in the evaluation history. The system now correctly logs and displays the actual model ID that received the feedback, restoring clarity and enabling proper analysis of model performance in arena environments.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eResolved Icon Overlap in 'Her' Theme\u003c/strong\u003e: Fixed a visual glitch in the 'Her' theme where icons would overlap on the loading screen and certain icons appeared incongruous. The display has been corrected to ensure proper visual presentation and theme consistency.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eResolved Critical OIDC SSO Login Failure\u003c/strong\u003e: Fixed a critical issue where OIDC Single Sign-On (SSO) logins failed due to an error in setting the authentication token as a cookie during the redirect process. This ensures reliable and seamless authentication for users utilizing OIDC providers, restoring full login functionality that was impacted by previous security hardening.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePrevented UI Blocking by Unreachable Webhooks\u003c/strong\u003e: Resolved a critical performance and user experience issue where synchronous webhook calls to unreachable or slow endpoints would block the entire user interface for all users. Webhook requests are now processed asynchronously using \u0026quot;aiohttp\u0026quot;, ensuring that the UI remains responsive and functional even if webhook delivery encounters delays or failures.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003ePassword Change Option Hidden for Externally Authenticated Users\u003c/strong\u003e: Resolved an issue where the password change dialog was visible to users authenticated via external methods (e.g., LDAP, OIDC, Trusted Header). The option to change a password in user settings is now correctly hidden for these users, as their passwords are managed externally, streamlining the user interface and preventing confusion.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Temporary Chat and Permission Enforcement Issues\u003c/strong\u003e: Fixed a bug where temporary chats (identified by \u0026quot;chat_id = local\u0026quot;) incorrectly triggered database checks, leading to 404 errors. This also resolves the issue where the 'USER_PERMISSIONS_CHAT_TEMPORARY_ENFORCED' setting was not functioning as intended, ensuring temporary chat mode now works correctly for user roles.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eAdmin Model Visibility for Administrators\u003c/strong\u003e: Private models remained visible and usable for administrators in the chat model selector, even when the intended privacy setting (\u0026quot;ENABLE_ADMIN_WORKSPACE_CONTENT_ACCESS\u0026quot; - now renamed to \u0026quot;BYPASS_ADMIN_ACCESS_CONTROL\u0026quot;) was disabled. This ensures consistent enforcement of model access controls and adherence to the principle of least privilege.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eClarified Web Search Engine Label for DDGS\u003c/strong\u003e: Addressed user confusion and inaccurate labeling by renaming \u0026quot;duckduckgo\u0026quot; to \u0026quot;DDGS\u0026quot; (Dux Distributed Global Search) in the web search engine selector. This clarifies that the system utilizes DDGS, a metasearch library that aggregates results from various search providers, accurately reflecting its underlying functionality rather than implying exclusive use of DuckDuckGo's search engine.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Settings UI Reactivity and Visibility\u003c/strong\u003e: Resolved an issue where settings tabs for 'Connections' and 'Tools' did not dynamically update their visibility based on global administrative feature flags (e.g., 'enable_direct_connections'). The UI now reactively shows or hides these sections, ensuring a consistent and clear experience when administrators control feature availability.\u003c/li\u003e\n\u003cli\u003e🎚️ \u003cstrong\u003eRestored Model and Banner Reordering Functionality\u003c/strong\u003e: Fixed a bug that prevented administrators from reordering models in the Admin Panel's 'Models' settings and banners in the 'Interface' settings via drag-and-drop. The sortable functionality has been restored, allowing for proper customization of display order.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eRestored Custom Pending User Overlay Visibility\u003c/strong\u003e: Fixed an issue where the custom title and description configured for pending users were not visible. The application now correctly exposes these UI configuration settings to pending users, ensuring that the custom onboarding messages are displayed as intended.\u003c/li\u003e\n\u003cli\u003e📥 \u003cstrong\u003eFixed Community Function Import Compatibility\u003c/strong\u003e: Resolved an issue that prevented the successful import of function files downloaded from openwebui.com due to schema differences. The system now correctly processes these files, allowing for seamless integration of community-contributed functions.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eFixed Stale Ollama Version in Docker Images\u003c/strong\u003e: Resolved an issue where the Ollama installation within Docker images could become stale due to caching during the build process. The Dockerfile now includes a mechanism to invalidate the build cache for the Ollama installation step, ensuring that the latest version of Ollama is always installed.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eImproved Milvus Query Handling for Large Datasets\u003c/strong\u003e: Fixed a \u0026quot;MilvusException\u0026quot; that occurred when attempting to query more than 16384 entries from a Milvus collection. The query logic has been refactored to use \u0026quot;query_iterator()\u0026quot;, enabling efficient fetching of larger result sets in batches and resolving the previous limitation on the number of entries that could be retrieved.\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eRestored Message Toolbar Icons for Empty Messages with Files\u003c/strong\u003e: Fixed an issue where the edit, copy, and delete icons were not displayed on user messages that contained an attached file but no text content. This ensures full interaction capabilities for all message types, allowing users to manage their messages consistently.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Streaming Interruption for Kimi-Dev Models\u003c/strong\u003e: Fixed an issue where streaming responses from Kimi-Dev models would halt prematurely upon encountering specific 'thinking' tokens (◁think▷, ◁/think▷). The system now correctly processes these tokens, ensuring uninterrupted streaming and proper handling of hidden or collapsible thinking sections.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eEnhanced Knowledge Base Search Functionality\u003c/strong\u003e: Improved the search capability within the 'Knowledge' section of the Workspace. Previously, searching for knowledge bases required exact term matches or starting with the first letter. Now, the search algorithm has been refined to allow broader, less exact matches, making it easier and more intuitive to find relevant knowledge bases.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eResolved Chinese Input 'Enter' Key Issue (macOS \u0026amp; iOS Safari)\u003c/strong\u003e: Fixed a bug where pressing the 'Enter' key during text composition with Input Method Editors (IMEs) on macOS and iOS Safari browsers would prematurely send the message. The system now robustly handles the composition state by addressing a 'compositionend' event bug specific to Safari, ensuring a smooth and expected typing experience for users of various languages, including Chinese and Korean.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eResolved OAUTH_GROUPS_CLAIM Configuration Issue\u003c/strong\u003e: Fixed a bug where the \u0026quot;OAUTH_GROUPS_CLAIM\u0026quot; environment variable was not correctly parsed due to a typo in the configuration file. This ensures that OAuth group management features, including automatic group creation, now correctly utilize the specified claim from the identity provider, allowing for seamless integration with external user directories like Keycloak.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eResolved Azure PostgreSQL pgvector Extension Permissions\u003c/strong\u003e: Fixed an issue preventing the creation of \u0026quot;pgvector\u0026quot; and \u0026quot;pgcrypto\u0026quot; extensions on Azure PostgreSQL Flexible Servers due to permission limitations (e.g., 'Only members of \u0026quot;azure_pg_admin\u0026quot; are allowed to use \u0026quot;CREATE EXTENSION\u0026quot;'). The extension creation process now includes a conditional check, ensuring seamless deployment and compatibility with Azure PostgreSQL environments even with restricted database user permissions.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Backend Path Resolution and Alembic Stability\u003c/strong\u003e: Fixed issues causing Alembic database migrations to fail due to incorrect path resolution within the application. By implementing canonical path resolution for core directories and refining Alembic configuration, the robustness and correctness of internal pathing have been significantly enhanced, ensuring reliable database operations.\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eResolved Arena Model Identification in Feedback History\u003c/strong\u003e: Fixed an issue where the model used for feedback in arena settings was incorrectly reported as 'arena-model' in the evaluation history. The system now correctly logs and displays the actual model ID that received the feedback, restoring clarity and enabling proper analysis of model performance in arena environments.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eResolved Icon Overlap in 'Her' Theme\u003c/strong\u003e: Fixed a visual glitch in the 'Her' theme where icons would overlap on the loading screen and certain icons appeared incongruous. The display has been corrected to ensure proper visual presentation and theme consistency.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eResolved Model Sorting TypeError with Null Names\u003c/strong\u003e: Fixed a \u0026quot;TypeError\u0026quot; that occurred in the \u0026quot;/api/models\u0026quot; endpoint when sorting models with null or missing names. The model sorting logic has been improved to gracefully handle such edge cases by ensuring that model IDs and names are treated as empty strings if their values are null or undefined, preventing comparison errors and improving API stability.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/407dc9a401fc2382df06d776dbd8ba95dffda38a\"\u003e\u003ccode\u003e407dc9a\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16507\"\u003e#16507\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9fb2c9c86d0dfb1416198befea37715d1be0eb06\"\u003e\u003ccode\u003e9fb2c9c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/60b8cfb9fa2228eac878c3c52eccdff7abc4d384\"\u003e\u003ccode\u003e60b8cfb\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5a66f69460381a81dfd8e98824b094557befbe8b\"\u003e\u003ccode\u003e5a66f69\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16779\"\u003e#16779\u003c/a\u003e from mahenning/fix--clean-unload-embed/reranker-models\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/578f116ebb95b03f0205f93b1fd66f71e92bb6e5\"\u003e\u003ccode\u003e578f116\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d3b5ba8472218cf1067475aafeb4c860f7998a19\"\u003e\u003ccode\u003ed3b5ba8\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16767\"\u003e#16767\u003c/a\u003e from Classic298/patch-2\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/3e28c46026687414290d13255f4d19fa7a1aecd9\"\u003e\u003ccode\u003e3e28c46\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/71d7ba6c07ce858ed9886928d398e66fa39cb6af\"\u003e\u003ccode\u003e71d7ba6\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16785\"\u003e#16785\u003c/a\u003e from ShirasawaSama/i18n/improve-chinese-translation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/581c0f137e5afcd56083071e01ac0ff26e5c82b1\"\u003e\u003ccode\u003e581c0f1\u003c/code\u003e\u003c/a\u003e i18n: improve chinese translation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f2e78d79407004dfe5bc40a6ef3e71bf4088d273\"\u003e\u003ccode\u003ef2e78d7\u003c/code\u003e\u003c/a\u003e More formatting\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.22...v0.6.23\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.22\u0026new-version=v0.6.23)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/5","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/5","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/5/packages"},{"uuid":"3314343338","node_id":"PR_kwDOPIpjyc6jRcl5","number":1,"state":"closed","title":"Bump open-webui/open-webui from 0.6.21 to v0.6.22","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-08-13T01:29:26.000Z","author_association":"NONE","state_reason":null,"created_at":"2025-08-12T13:44:36.000Z","updated_at":"2025-08-13T01:29:27.000Z","time_to_close":42290,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.21","new_version":"v0.6.22","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.21 to v0.6.22.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.22\u003c/h2\u003e\n\u003ch2\u003e[0.6.22] - 2025-08-11\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eOpenAI API '/v1' Endpoint Compatibility\u003c/strong\u003e: Enhanced API compatibility by supporting requests to paths like '/v1/models', '/v1/embeddings', and '/v1/chat/completions'. This allows Open WebUI to integrate more seamlessly with tools that expect OpenAI's '/v1' API structure.\u003c/li\u003e\n\u003cli\u003e🪄 \u003cstrong\u003eToggle for Guided Response Regeneration Menu\u003c/strong\u003e: Introduced a new setting in 'Interface' settings, providing the ability to enable or disable the expanded guided response regeneration menu. This offers users more control over their chat workflow and interface preferences.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eGeneral UI/UX Enhancements\u003c/strong\u003e: Implemented various user interface and experience improvements, including more rounded corners for cards in the Knowledge, Prompts, and Tools sections, and minor layout adjustments within the chat Navbar for improved visual consistency.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Introduced support for the Kabyle (Taqbaylit) language, refined and expanded translations for Chinese, expanding the platform's linguistic coverage.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🐞 \u003cstrong\u003eOpenAI Error Message Propagation\u003c/strong\u003e: Resolved an issue where specific OpenAI API errors (e.g., 'Organization Not Verified') were obscured by generic 'JSONResponse' iterable errors. The system now correctly propagates detailed and actionable error messages from OpenAI to the user.\u003c/li\u003e\n\u003cli\u003e🌲 \u003cstrong\u003ePinecone Insert Issue\u003c/strong\u003e: Fixed a bug that prevented proper insertion of items into Pinecone vector databases.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eS3 Vector Issue\u003c/strong\u003e: Resolved a bug where s3vector functionality failed due to incorrect import paths.\u003c/li\u003e\n\u003cli\u003e🏠 \u003cstrong\u003eLanding Page Option Setting Not Working\u003c/strong\u003e: Fixed an issue where the landing page option in settings was not functioning as intended.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/blockquote\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.22] - 2025-08-11\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eOpenAI API '/v1' Endpoint Compatibility\u003c/strong\u003e: Enhanced API compatibility by supporting requests to paths like '/v1/models', '/v1/embeddings', and '/v1/chat/completions'. This allows Open WebUI to integrate more seamlessly with tools that expect OpenAI's '/v1' API structure.\u003c/li\u003e\n\u003cli\u003e🪄 \u003cstrong\u003eToggle for Guided Response Regeneration Menu\u003c/strong\u003e: Introduced a new setting in 'Interface' settings, providing the ability to enable or disable the expanded guided response regeneration menu. This offers users more control over their chat workflow and interface preferences.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eGeneral UI/UX Enhancements\u003c/strong\u003e: Implemented various user interface and experience improvements, including more rounded corners for cards in the Knowledge, Prompts, and Tools sections, and minor layout adjustments within the chat Navbar for improved visual consistency.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Introduced support for the Kabyle (Taqbaylit) language, refined and expanded translations for Chinese, expanding the platform's linguistic coverage.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🐞 \u003cstrong\u003eOpenAI Error Message Propagation\u003c/strong\u003e: Resolved an issue where specific OpenAI API errors (e.g., 'Organization Not Verified') were obscured by generic 'JSONResponse' iterable errors. The system now correctly propagates detailed and actionable error messages from OpenAI to the user.\u003c/li\u003e\n\u003cli\u003e🌲 \u003cstrong\u003ePinecone Insert Issue\u003c/strong\u003e: Fixed a bug that prevented proper insertion of items into Pinecone vector databases.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eS3 Vector Issue\u003c/strong\u003e: Resolved a bug where s3vector functionality failed due to incorrect import paths.\u003c/li\u003e\n\u003cli\u003e🏠 \u003cstrong\u003eLanding Page Option Setting Not Working\u003c/strong\u003e: Fixed an issue where the landing page option in settings was not functioning as intended.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/blockquote\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/438e5d966f0f64f9ea3feab22724a5bd96a4127b\"\u003e\u003ccode\u003e438e5d9\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16456\"\u003e#16456\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/17cc3b7d729dbb2e1f274b7c038b6bd55318db19\"\u003e\u003ccode\u003e17cc3b7\u003c/code\u003e\u003c/a\u003e fix: chat item generate title button\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d89c5b6c30cb85f7c84f4a18aa25a856464110bb\"\u003e\u003ccode\u003ed89c5b6\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8fd5006b6fe8536275af6f17e420ad4a669374d0\"\u003e\u003ccode\u003e8fd5006\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/97448e25eceea278406e56b578fa24cec949661f\"\u003e\u003ccode\u003e97448e2\u003c/code\u003e\u003c/a\u003e fix: openai error handling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8916a284bd729e538a185f73567cb272b85aef76\"\u003e\u003ccode\u003e8916a28\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8e2aaaf94f39983b2b1efe8b468f5e7b4887ca37\"\u003e\u003ccode\u003e8e2aaaf\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e15f8b8bafa66babd3eb44dcc4d834ff6f8c44f4\"\u003e\u003ccode\u003ee15f8b8\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16458\"\u003e#16458\u003c/a\u003e from Classic298/patch-3\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/890691319f4af2e8db5ef49b0a6dc825607e080b\"\u003e\u003ccode\u003e8906913\u003c/code\u003e\u003c/a\u003e fix: s3vector import issue\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/21094ca88b4ae806d33d0759904c9dc9f08f1dee\"\u003e\u003ccode\u003e21094ca\u003c/code\u003e\u003c/a\u003e fix: pinecone insert issue\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.21...v0.6.22\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.21\u0026new-version=v0.6.22)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/1","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/1","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/1/packages"},{"uuid":"2683380391","node_id":"PR_kwDOM-FVBM6f8SKn","number":76,"state":"open","title":"Bump open-webui/open-webui from v0.5.20 to 0.6.18 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-07-21T22:55:02.000Z","updated_at":"2025-07-21T22:55:03.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"0.6.18","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to 0.6.18.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.18\u003c/h2\u003e\n\u003ch2\u003e[0.6.18] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚑 \u003cstrong\u003eUsers Not Loading in Groups\u003c/strong\u003e: Resolved an issue where user list was not displaying within user groups, restoring full visibility and management of group memberships for teams and admins.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.17\u003c/h2\u003e\n\u003ch2\u003e[0.6.17] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📂 \u003cstrong\u003eDedicated Folder View with Chat List\u003c/strong\u003e: Clicking a folder now reveals a brand-new landing page showcasing a list of all chats within that folder, making navigation simpler and giving teams immediate visibility into project-specific conversations.\u003c/li\u003e\n\u003cli\u003e🆕 \u003cstrong\u003eStreamlined Folder Creation Modal\u003c/strong\u003e: Creating a new folder is now a seamless, unified experience with a dedicated modal that visually and functionally matches the edit folder flow, making workspace organization more intuitive and error-free for all users.\u003c/li\u003e\n\u003cli\u003e🗃️ \u003cstrong\u003eDirect File Uploads to Folder Knowledge\u003c/strong\u003e: You can now upload files straight to a folder’s knowledge—empowering you to enrich project spaces by adding resources and documents directly, without the need to pre-create knowledge bases beforehand.\u003c/li\u003e\n\u003cli\u003e🔎 \u003cstrong\u003eChat Preview in Search\u003c/strong\u003e: When searching chats, instantly preview results in context without having to open them—making discovery, auditing, and recall dramatically quicker, especially in large, active teams.\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Upload and Inline Insertion in Notes\u003c/strong\u003e: Notes now support inserting images directly among your text, letting you create rich, visually structured documentation, brainstorms, or reports in a more natural and engaging way—no more images just as attachments.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eEnhanced Note Selection Editing and Q\u0026amp;A\u003c/strong\u003e: Select any portion of your notes to either edit just the highlighted part or ask focused questions about that content—streamlining workflows, boosting productivity, and making reviews or AI-powered enhancements more targeted.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCopy Notes as Rich Text\u003c/strong\u003e: Copy entire notes—including all formatting, images, and structure—directly as rich text for seamless pasting into emails, reports, or other tools, maintaining clarity and consistency outside the WebUI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFade-In Streaming Text Experience\u003c/strong\u003e: Live-generated responses now elegantly fade in as the AI streams them, creating a more natural and visually engaging reading experience; easily toggled off in Interface settings if you prefer static displays.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSettings for Follow-Up Prompts\u003c/strong\u003e: Fine-tune your follow-up prompt experience—with new controls, you can choose to keep them visible or have them inserted directly into the message input instead of auto-submitting, giving you more flexibility and control over your workflow.\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003ePrompt Variable Documentation Quick Link\u003c/strong\u003e: Access documentation for prompt variables in one click from the prompt editor modal—shortening the learning curve and making advanced prompt-building more accessible.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eActive and Total User Metrics for Telemetry\u003c/strong\u003e: Gain valuable insights into usage patterns and platform engagement with new metrics tracking active and total users—enhancing auditability and planning for large organizations.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eTraceability with Log Trace and Span IDs\u003c/strong\u003e: Each log entry now carries detailed trace and span IDs, making it much easier for admins to pinpoint and resolve issues across distributed systems or in complex troubleshooting.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eUser Group Add/Remove Endpoints\u003c/strong\u003e: Effortlessly add or remove users from groups with new, improved endpoints—giving admins and team leads faster, clearer control over collaboration and permissions.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eNote Settings and Controls Streamlined\u003c/strong\u003e: The main “Settings” for notes are now simply called “Controls”, and note files now reside in a dedicated controls section, decluttering navigation and making it easier to find and configure note-related options.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eFaster Admin User Page Loads\u003c/strong\u003e: The user list endpoint for admins has been optimized to exclude heavy profile images, speeding up load times for large teams and reducing waiting during administrative tasks.\u003c/li\u003e\n\u003cli\u003e📡 \u003cstrong\u003eChat ID Header Forwarding\u003c/strong\u003e: Ollama and OpenAI router requests now include the chat ID in request headers, enabling better request correlation and debugging capabilities across AI model integrations.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEnhanced Reasoning Tag Processing\u003c/strong\u003e: Improved and expanded reasoning tag parsing to handle various tag formats more robustly, including standard XML-style tags and custom delimiters, ensuring better AI reasoning transparency and debugging capabilities.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth Token Endpoint Authentication Method\u003c/strong\u003e: Added configurable OAuth token endpoint authentication method support, providing enhanced flexibility and security options for enterprise OAuth integrations and identity provider compatibility.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis Sentinel High Availability Support\u003c/strong\u003e: Comprehensive Redis Sentinel failover implementation with automatic master discovery, intelligent retry logic for connection failures, and seamless operation during master node outages—eliminating single points of failure and ensuring continuous service availability in production deployments.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Refined and expanded translations for Simplified Chinese, Traditional Chinese, French, German, Korean, and Polish, ensuring a more fluent and native experience for global users across all supported languages.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eHybrid Search Functionality Restored\u003c/strong\u003e: Hybrid search now works seamlessly again—enabling more accurate, relevant, and comprehensive knowledge discovery across all RAG-powered workflows.\u003c/li\u003e\n\u003cli\u003e🚦 \u003cstrong\u003eNote Chat - Edit Button Disabled During AI Generation\u003c/strong\u003e: The edit button when chatting with a note is now disabled while the AI is responding—preventing accidental edits and ensuring workflow clarity during chat sessions.\u003c/li\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eCleaner Database Credentials\u003c/strong\u003e: Database connection no longer duplicates ‘@’ in credentials, preventing potential connection issues and ensuring smoother, more reliable integrations.\u003c/li\u003e\n\u003cli\u003e🧑‍💻 \u003cstrong\u003eFile Deletion Now Removes Related Vector Data\u003c/strong\u003e: When files are deleted from storage, they are now purged from the vector database as well, ensuring clean data management and preventing clutter or stale search results.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eFiles Modal Translation Issues Fixed\u003c/strong\u003e: All modal dialog strings—including “Using Entire Document” and “Using Focused Retrieval”—are now fully translated for a more consistent and localized UI experience.\u003c/li\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eDrag-and-Drop File Upload Disabled for Unsupported Models\u003c/strong\u003e: File upload by drag-and-drop is disabled when using models that do not support attachments—removing confusion and preventing workflow interruptions.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eOllama Tool Calls Now Reliable\u003c/strong\u003e: Fixed issues with Ollama-based tool calls, ensuring uninterrupted AI augmentation and tool use for every chat.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eMIME Type Help String Correction\u003c/strong\u003e: Cleaned up mimetype help text by removing extraneous characters, providing clearer guidance for file upload configurations.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eNote Editor Permission Fix\u003c/strong\u003e: Removed unnecessary admin-only restriction from note chat functionality, allowing all authorized users to access note editing features as intended.\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eChat Sources Handling Improved\u003c/strong\u003e: Fixed sources handling logic to prevent duplicate source assignments in chat messages, ensuring cleaner and more accurate source attribution during conversations.\u003c/li\u003e\n\u003cli\u003e😀 \u003cstrong\u003eEmoji Generation Error Handling\u003c/strong\u003e: Improved error handling in audio router and fixed metadata structure for emoji generation tasks, preventing crashes and ensuring more reliable emoji generation functionality.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eFolder System Prompt Permission Enforcement\u003c/strong\u003e: System prompt fields in folder edit modal are now properly hidden for users without system prompt permissions, ensuring consistent security policy enforcement across all folder management interfaces.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eWebSocket Redis Lock Timeout Type Conversion\u003c/strong\u003e: Fixed proper integer type conversion for WebSocket Redis lock timeout configuration with robust error handling, preventing potential configuration errors and ensuring stable WebSocket connections.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003ePostHog Dependency Added\u003c/strong\u003e: Added PostHog 5.4.0 library to resolve ChromaDB compatibility issues, ensuring stable vector database operations and preventing library version conflicts during deployment.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.18] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚑 \u003cstrong\u003eUsers Not Loading in Groups\u003c/strong\u003e: Resolved an issue where user list was not displaying within user groups, restoring full visibility and management of group memberships for teams and admins.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.17] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📂 \u003cstrong\u003eDedicated Folder View with Chat List\u003c/strong\u003e: Clicking a folder now reveals a brand-new landing page showcasing a list of all chats within that folder, making navigation simpler and giving teams immediate visibility into project-specific conversations.\u003c/li\u003e\n\u003cli\u003e🆕 \u003cstrong\u003eStreamlined Folder Creation Modal\u003c/strong\u003e: Creating a new folder is now a seamless, unified experience with a dedicated modal that visually and functionally matches the edit folder flow, making workspace organization more intuitive and error-free for all users.\u003c/li\u003e\n\u003cli\u003e🗃️ \u003cstrong\u003eDirect File Uploads to Folder Knowledge\u003c/strong\u003e: You can now upload files straight to a folder’s knowledge—empowering you to enrich project spaces by adding resources and documents directly, without the need to pre-create knowledge bases beforehand.\u003c/li\u003e\n\u003cli\u003e🔎 \u003cstrong\u003eChat Preview in Search\u003c/strong\u003e: When searching chats, instantly preview results in context without having to open them—making discovery, auditing, and recall dramatically quicker, especially in large, active teams.\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Upload and Inline Insertion in Notes\u003c/strong\u003e: Notes now support inserting images directly among your text, letting you create rich, visually structured documentation, brainstorms, or reports in a more natural and engaging way—no more images just as attachments.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eEnhanced Note Selection Editing and Q\u0026amp;A\u003c/strong\u003e: Select any portion of your notes to either edit just the highlighted part or ask focused questions about that content—streamlining workflows, boosting productivity, and making reviews or AI-powered enhancements more targeted.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCopy Notes as Rich Text\u003c/strong\u003e: Copy entire notes—including all formatting, images, and structure—directly as rich text for seamless pasting into emails, reports, or other tools, maintaining clarity and consistency outside the WebUI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFade-In Streaming Text Experience\u003c/strong\u003e: Live-generated responses now elegantly fade in as the AI streams them, creating a more natural and visually engaging reading experience; easily toggled off in Interface settings if you prefer static displays.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSettings for Follow-Up Prompts\u003c/strong\u003e: Fine-tune your follow-up prompt experience—with new controls, you can choose to keep them visible or have them inserted directly into the message input instead of auto-submitting, giving you more flexibility and control over your workflow.\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003ePrompt Variable Documentation Quick Link\u003c/strong\u003e: Access documentation for prompt variables in one click from the prompt editor modal—shortening the learning curve and making advanced prompt-building more accessible.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eActive and Total User Metrics for Telemetry\u003c/strong\u003e: Gain valuable insights into usage patterns and platform engagement with new metrics tracking active and total users—enhancing auditability and planning for large organizations.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eTraceability with Log Trace and Span IDs\u003c/strong\u003e: Each log entry now carries detailed trace and span IDs, making it much easier for admins to pinpoint and resolve issues across distributed systems or in complex troubleshooting.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eUser Group Add/Remove Endpoints\u003c/strong\u003e: Effortlessly add or remove users from groups with new, improved endpoints—giving admins and team leads faster, clearer control over collaboration and permissions.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eNote Settings and Controls Streamlined\u003c/strong\u003e: The main “Settings” for notes are now simply called “Controls”, and note files now reside in a dedicated controls section, decluttering navigation and making it easier to find and configure note-related options.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eFaster Admin User Page Loads\u003c/strong\u003e: The user list endpoint for admins has been optimized to exclude heavy profile images, speeding up load times for large teams and reducing waiting during administrative tasks.\u003c/li\u003e\n\u003cli\u003e📡 \u003cstrong\u003eChat ID Header Forwarding\u003c/strong\u003e: Ollama and OpenAI router requests now include the chat ID in request headers, enabling better request correlation and debugging capabilities across AI model integrations.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEnhanced Reasoning Tag Processing\u003c/strong\u003e: Improved and expanded reasoning tag parsing to handle various tag formats more robustly, including standard XML-style tags and custom delimiters, ensuring better AI reasoning transparency and debugging capabilities.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth Token Endpoint Authentication Method\u003c/strong\u003e: Added configurable OAuth token endpoint authentication method support, providing enhanced flexibility and security options for enterprise OAuth integrations and identity provider compatibility.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis Sentinel High Availability Support\u003c/strong\u003e: Comprehensive Redis Sentinel failover implementation with automatic master discovery, intelligent retry logic for connection failures, and seamless operation during master node outages—eliminating single points of failure and ensuring continuous service availability in production deployments.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Refined and expanded translations for Simplified Chinese, Traditional Chinese, French, German, Korean, and Polish, ensuring a more fluent and native experience for global users across all supported languages.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eHybrid Search Functionality Restored\u003c/strong\u003e: Hybrid search now works seamlessly again—enabling more accurate, relevant, and comprehensive knowledge discovery across all RAG-powered workflows.\u003c/li\u003e\n\u003cli\u003e🚦 \u003cstrong\u003eNote Chat - Edit Button Disabled During AI Generation\u003c/strong\u003e: The edit button when chatting with a note is now disabled while the AI is responding—preventing accidental edits and ensuring workflow clarity during chat sessions.\u003c/li\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eCleaner Database Credentials\u003c/strong\u003e: Database connection no longer duplicates ‘@’ in credentials, preventing potential connection issues and ensuring smoother, more reliable integrations.\u003c/li\u003e\n\u003cli\u003e🧑‍💻 \u003cstrong\u003eFile Deletion Now Removes Related Vector Data\u003c/strong\u003e: When files are deleted from storage, they are now purged from the vector database as well, ensuring clean data management and preventing clutter or stale search results.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eFiles Modal Translation Issues Fixed\u003c/strong\u003e: All modal dialog strings—including “Using Entire Document” and “Using Focused Retrieval”—are now fully translated for a more consistent and localized UI experience.\u003c/li\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eDrag-and-Drop File Upload Disabled for Unsupported Models\u003c/strong\u003e: File upload by drag-and-drop is disabled when using models that do not support attachments—removing confusion and preventing workflow interruptions.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eOllama Tool Calls Now Reliable\u003c/strong\u003e: Fixed issues with Ollama-based tool calls, ensuring uninterrupted AI augmentation and tool use for every chat.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eMIME Type Help String Correction\u003c/strong\u003e: Cleaned up mimetype help text by removing extraneous characters, providing clearer guidance for file upload configurations.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eNote Editor Permission Fix\u003c/strong\u003e: Removed unnecessary admin-only restriction from note chat functionality, allowing all authorized users to access note editing features as intended.\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eChat Sources Handling Improved\u003c/strong\u003e: Fixed sources handling logic to prevent duplicate source assignments in chat messages, ensuring cleaner and more accurate source attribution during conversations.\u003c/li\u003e\n\u003cli\u003e😀 \u003cstrong\u003eEmoji Generation Error Handling\u003c/strong\u003e: Improved error handling in audio router and fixed metadata structure for emoji generation tasks, preventing crashes and ensuring more reliable emoji generation functionality.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eFolder System Prompt Permission Enforcement\u003c/strong\u003e: System prompt fields in folder edit modal are now properly hidden for users without system prompt permissions, ensuring consistent security policy enforcement across all folder management interfaces.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eWebSocket Redis Lock Timeout Type Conversion\u003c/strong\u003e: Fixed proper integer type conversion for WebSocket Redis lock timeout configuration with robust error handling, preventing potential configuration errors and ensuring stable WebSocket connections.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003ePostHog Dependency Added\u003c/strong\u003e: Added PostHog 5.4.0 library to resolve ChromaDB compatibility issues, ensuring stable vector database operations and preventing library version conflicts during deployment.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5fbfe2bdcadf5f157926f6551891e4dc0802b9f3\"\u003e\u003ccode\u003e5fbfe2b\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15879\"\u003e#15879\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/6e0328798db704418391dd0ee2a631c41f8f507e\"\u003e\u003ccode\u003e6e03287\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0119036a117cdd4da6749b6cd043b8aa2a212c8b\"\u003e\u003ccode\u003e0119036\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15871\"\u003e#15871\u003c/a\u003e from Classic298/cors\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7a023e0841076e53f388b60cae37443adcffbd6f\"\u003e\u003ccode\u003e7a023e0\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15875\"\u003e#15875\u003c/a\u003e from leebeomhun/i18n-ko\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b397008ee06993814ea85dfde1e2cbc6380eab01\"\u003e\u003ccode\u003eb397008\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b329c63c80ff092e7894b1f4769c4d9a73668a35\"\u003e\u003ccode\u003eb329c63\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/95b11207a12d7811dfc0b78bf082e50c43ffc693\"\u003e\u003ccode\u003e95b1120\u003c/code\u003e\u003c/a\u003e fix: group user load\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/74d0e6b2c7501026153d56e44b2d64b5b1499720\"\u003e\u003ccode\u003e74d0e6b\u003c/code\u003e\u003c/a\u003e i18n korean Fix typo\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7ffc12567f81d47a761afc64131c809cc094905a\"\u003e\u003ccode\u003e7ffc125\u003c/code\u003e\u003c/a\u003e i18n update and fix:ko-KR translation.json\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d8ed4fa0c270ba1ecba08362a4e52204b9c65b80\"\u003e\u003ccode\u003ed8ed4fa\u003c/code\u003e\u003c/a\u003e Merge branch 'open-webui:main' into cors\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.18\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=0.6.18)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/76","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/76","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/76/packages"},{"uuid":"2665558087","node_id":"PR_kwDOM-FVBM6e4TBH","number":75,"state":"open","title":"Bump open-webui/open-webui from v0.5.20 to v0.6.16 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-07-14T22:33:35.000Z","updated_at":"2025-07-14T22:33:35.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"v0.6.16","repository_url":null}],"path":"/docker","ecosystem":"docker"},"body":"\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=v0.6.16)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/75","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/75","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/75/packages"},{"uuid":"2633773563","node_id":"PR_kwDONjNt7s6c_DH7","number":6,"state":"open","title":"Bump open-webui/open-webui from `4583b43` to `07d6e7b`","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-07-01T22:18:24.000Z","updated_at":"2025-07-01T22:18:25.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"`4583b43`","new_version":"`07d6e7b`","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from `4583b43` to `07d6e7b`.\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch1\u003eChangelog\u003c/h1\u003e\n\u003cp\u003eAll notable changes to this project will be documented in this file.\u003c/p\u003e\n\u003cp\u003eThe format is based on \u003ca href=\"https://keepachangelog.com/en/1.1.0/\"\u003eKeep a Changelog\u003c/a\u003e,\nand this project adheres to \u003ca href=\"https://semver.org/spec/v2.0.0.html\"\u003eSemantic Versioning\u003c/a\u003e.\u003c/p\u003e\n\u003ch2\u003e[0.6.15] - 2025-06-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eGlobal Image Compression Option\u003c/strong\u003e: Effortlessly set image compression globally so all image uploads and outputs are optimized, speeding up load times and saving bandwidth—perfect for teams dealing with large files or limited network resources.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eCustom Speech-to-Text Content-Type for Transcription\u003c/strong\u003e: Define custom content types for audio transcription, ensuring compatibility with diverse audio sources and unlocking smoother, more accurate transcriptions in advanced setups.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLDAP Group Synchronization (Experimental)\u003c/strong\u003e: Automatically sync user groups from your LDAP directory directly into Open WebUI for seamless enterprise access management—simplifies identity integration and governance across your organization.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eOpenTelemetry Metrics via OTLP Exporter (Experimental)\u003c/strong\u003e: Gain enterprise-grade analytics and monitor your AI usage in real time with experimental OpenTelemetry Metrics support—connect to any OTLP-compatible backend for instant insights into performance, load, and user interactions.\u003c/li\u003e\n\u003cli\u003e🕰️ \u003cstrong\u003eSee User Message Timestamps on Hover (Chat Bubble UI)\u003c/strong\u003e: Effortlessly check when any user message was sent by hovering over it in Chat Bubble mode—no more switching screens or digging through logs for context.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLeaderboard Sorting Options\u003c/strong\u003e: Sort the leaderboard directly in the UI for a clearer, more actionable view of top performers, models, or tools—making analysis and recognition quick and easy for teams.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eEvaluation Details Modal in Feedbacks and Leaderboard\u003c/strong\u003e: Dive deeper with new modals that display detailed evaluation information when reviewing feedbacks and leaderboard rankings—accelerates learning, progress tracking, and quality improvement.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSupport for Multiple Pages in External Document Loaders\u003c/strong\u003e: Effortlessly extract and work with content spanning multiple pages in external documents, giving you complete flexibility for in-depth research and document workflows.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eNew Accessibility Enhancements Across the Interface\u003c/strong\u003e: Benefit from significant accessibility improvements—tab navigation, ARIA roles/labels, better high-contrast text/modes, accessible modals, and more—making Open WebUI more usable and equitable for everyone, including those using assistive technologies.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePerformance \u0026amp; Stability Upgrades Across Frontend and Backend\u003c/strong\u003e: Enjoy a smoother, more reliable experience with numerous behind-the-scenes optimizations and refactoring on both frontend and backend—resulting in faster load times, fewer errors, and even greater stability throughout your workflows.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eUpdated and Expanded Localizations\u003c/strong\u003e: Enjoy improved, up-to-date translations for Finnish, German (now with model pinning features), Korean, Russian, Simplified Chinese, Spanish, and more—making every interaction smoother, clearer, and more intuitive for international users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🦾 \u003cstrong\u003eOllama Error Messages More Descriptive\u003c/strong\u003e: Receive clearer, more actionable error messages when something goes wrong with Ollama models—making troubleshooting and user support faster and more effective.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Webloader Now Works as Expected\u003c/strong\u003e: Resolved an issue where the \u0026quot;bypass webloader\u0026quot; feature failed to function correctly, ensuring web search bypasses operate smoothly and reliably for lighter, faster query results.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003ePrevent Redundant Documents in Citation List\u003c/strong\u003e: The expanded citation list no longer shows duplicate documents, offering a cleaner, easier-to-digest reference experience when reviewing sources in knowledge and research workflows.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eTrusted Header Email Matching is Now Case-Insensitive\u003c/strong\u003e: Fixed a critical authentication issue where email case sensitivity could cause secure headers to mismatch, ensuring robust, seamless login and session management in all environments.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eDirect Tool Server Input Accepts Empty Strings\u003c/strong\u003e: You can now submit direct tool server commands without unexpected errors when passing empty-string values, improving integration and automation efficiency.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eCitation Page Number for Page 1 is Now Displayed\u003c/strong\u003e: Corrected an oversight where references for page 1 documents were missing the page number; citations are now always accurate and fully visible.\u003c/li\u003e\n\u003cli\u003e📒 \u003cstrong\u003eNotes Access Restored\u003c/strong\u003e: Fixed an issue where some users could not access their notes—everyone can now view and manage their notes reliably, ensuring seamless documentation and workflow continuity.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eOAuth Callback Double-Slash Issue Resolved\u003c/strong\u003e: Fixed rare cases where an extra slash in OAuth callbacks caused failed logins or redirects, making third-party login integrations more reliable.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eDedicated Permission for System Prompts\u003c/strong\u003e: System prompt access is now controlled by its own specific permission instead of being grouped with general chat controls, empowering admins with finer-grained management over who can view or modify system prompts for enhanced security and workflow customization.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eYouTube Transcript API and python-pptx Updated\u003c/strong\u003e: Enjoy better performance, reliability, and broader compatibility thanks to underlying library upgrades—less friction with media-rich and presentation workflows.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eConsole Logging Disabled in Production\u003c/strong\u003e: All 'console.log' and 'console.debug' statements are now disabled in production, guaranteeing improved security and cleaner browser logs for end users by removing extraneous technical output.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003eSee full diff in \u003ca href=\"https://github.com/open-webui/open-webui/commits\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=main\u0026new-version=main)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/ArloL/open-webui-runner/pull/6","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArloL%2Fopen-webui-runner/issues/6","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/6/packages"},{"uuid":"3151274888","node_id":"PR_kwDOM-FVBM6ayQz0","number":68,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to 0.6.15 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-07-14T22:33:37.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-06-16T20:46:37.000Z","updated_at":"2025-07-14T22:33:37.000Z","time_to_close":2425620,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"0.6.15","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to 0.6.15.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.15\u003c/h2\u003e\n\u003ch2\u003e[0.6.15] - 2025-06-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eGlobal Image Compression Option\u003c/strong\u003e: Effortlessly set image compression globally so all image uploads and outputs are optimized, speeding up load times and saving bandwidth—perfect for teams dealing with large files or limited network resources.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eCustom Speech-to-Text Content-Type for Transcription\u003c/strong\u003e: Define custom content types for audio transcription, ensuring compatibility with diverse audio sources and unlocking smoother, more accurate transcriptions in advanced setups.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLDAP Group Synchronization (Experimental)\u003c/strong\u003e: Automatically sync user groups from your LDAP directory directly into Open WebUI for seamless enterprise access management—simplifies identity integration and governance across your organization.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eOpenTelemetry Metrics via OTLP Exporter (Experimental)\u003c/strong\u003e: Gain enterprise-grade analytics and monitor your AI usage in real time with experimental OpenTelemetry Metrics support—connect to any OTLP-compatible backend for instant insights into performance, load, and user interactions.\u003c/li\u003e\n\u003cli\u003e🕰️ \u003cstrong\u003eSee User Message Timestamps on Hover (Chat Bubble UI)\u003c/strong\u003e: Effortlessly check when any user message was sent by hovering over it in Chat Bubble mode—no more switching screens or digging through logs for context.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLeaderboard Sorting Options\u003c/strong\u003e: Sort the leaderboard directly in the UI for a clearer, more actionable view of top performers, models, or tools—making analysis and recognition quick and easy for teams.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eEvaluation Details Modal in Feedbacks and Leaderboard\u003c/strong\u003e: Dive deeper with new modals that display detailed evaluation information when reviewing feedbacks and leaderboard rankings—accelerates learning, progress tracking, and quality improvement.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSupport for Multiple Pages in External Document Loaders\u003c/strong\u003e: Effortlessly extract and work with content spanning multiple pages in external documents, giving you complete flexibility for in-depth research and document workflows.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eNew Accessibility Enhancements Across the Interface\u003c/strong\u003e: Benefit from significant accessibility improvements—tab navigation, ARIA roles/labels, better high-contrast text/modes, accessible modals, and more—making Open WebUI more usable and equitable for everyone, including those using assistive technologies.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePerformance \u0026amp; Stability Upgrades Across Frontend and Backend\u003c/strong\u003e: Enjoy a smoother, more reliable experience with numerous behind-the-scenes optimizations and refactoring on both frontend and backend—resulting in faster load times, fewer errors, and even greater stability throughout your workflows.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eUpdated and Expanded Localizations\u003c/strong\u003e: Enjoy improved, up-to-date translations for Finnish, German (now with model pinning features), Korean, Russian, Simplified Chinese, Spanish, and more—making every interaction smoother, clearer, and more intuitive for international users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🦾 \u003cstrong\u003eOllama Error Messages More Descriptive\u003c/strong\u003e: Receive clearer, more actionable error messages when something goes wrong with Ollama models—making troubleshooting and user support faster and more effective.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Webloader Now Works as Expected\u003c/strong\u003e: Resolved an issue where the \u0026quot;bypass webloader\u0026quot; feature failed to function correctly, ensuring web search bypasses operate smoothly and reliably for lighter, faster query results.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003ePrevent Redundant Documents in Citation List\u003c/strong\u003e: The expanded citation list no longer shows duplicate documents, offering a cleaner, easier-to-digest reference experience when reviewing sources in knowledge and research workflows.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eTrusted Header Email Matching is Now Case-Insensitive\u003c/strong\u003e: Fixed a critical authentication issue where email case sensitivity could cause secure headers to mismatch, ensuring robust, seamless login and session management in all environments.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eDirect Tool Server Input Accepts Empty Strings\u003c/strong\u003e: You can now submit direct tool server commands without unexpected errors when passing empty-string values, improving integration and automation efficiency.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eCitation Page Number for Page 1 is Now Displayed\u003c/strong\u003e: Corrected an oversight where references for page 1 documents were missing the page number; citations are now always accurate and fully visible.\u003c/li\u003e\n\u003cli\u003e📒 \u003cstrong\u003eNotes Access Restored\u003c/strong\u003e: Fixed an issue where some users could not access their notes—everyone can now view and manage their notes reliably, ensuring seamless documentation and workflow continuity.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eOAuth Callback Double-Slash Issue Resolved\u003c/strong\u003e: Fixed rare cases where an extra slash in OAuth callbacks caused failed logins or redirects, making third-party login integrations more reliable.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eDedicated Permission for System Prompts\u003c/strong\u003e: System prompt access is now controlled by its own specific permission instead of being grouped with general chat controls, empowering admins with finer-grained management over who can view or modify system prompts for enhanced security and workflow customization.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eYouTube Transcript API and python-pptx Updated\u003c/strong\u003e: Enjoy better performance, reliability, and broader compatibility thanks to underlying library upgrades—less friction with media-rich and presentation workflows.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eConsole Logging Disabled in Production\u003c/strong\u003e: All 'console.log' and 'console.debug' statements are now disabled in production, guaranteeing improved security and cleaner browser logs for end users by removing extraneous technical output.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:\n\u003ca href=\"https://github.com/SadmL\"\u003e\u003ccode\u003e@​SadmL\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Bek85\"\u003e\u003ccode\u003e@​Bek85\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/vaclcer\"\u003e\u003ccode\u003e@​vaclcer\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/2underscores\"\u003e\u003ccode\u003e@​2underscores\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Ithanil\"\u003e\u003ccode\u003e@​Ithanil\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/ayanahye\"\u003e\u003ccode\u003e@​ayanahye\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/qingchunnh\"\u003e\u003ccode\u003e@​qingchunnh\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Kylapaallikko\"\u003e\u003ccode\u003e@​Kylapaallikko\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/silentoplayz\"\u003e\u003ccode\u003e@​silentoplayz\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/t-rekttt\"\u003e\u003ccode\u003e@​t-rekttt\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/jk-f5\"\u003e\u003ccode\u003e@​jk-f5\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/tcx4c70\"\u003e\u003ccode\u003e@​tcx4c70\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/williamgateszhao\"\u003e\u003ccode\u003e@​williamgateszhao\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/rgaricano\"\u003e\u003ccode\u003e@​rgaricano\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/sreesdas\"\u003e\u003ccode\u003e@​sreesdas\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Classic298\"\u003e\u003ccode\u003e@​Classic298\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/jackthgu\"\u003e\u003ccode\u003e@​jackthgu\u003c/code\u003e\u003c/a\u003e\u003c/p\u003e\n\u003ch2\u003eSponsors 🙌\u003c/h2\u003e\n\u003cp\u003e🚀 We'd like to extend a heartfelt thank you to our amazing sponsors for their generous support (Note: We've excluded private sponsors from this list. If you'd like to get featured here, feel free to reach out to us!)\u003c/p\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.15] - 2025-06-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eGlobal Image Compression Option\u003c/strong\u003e: Effortlessly set image compression globally so all image uploads and outputs are optimized, speeding up load times and saving bandwidth—perfect for teams dealing with large files or limited network resources.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eCustom Speech-to-Text Content-Type for Transcription\u003c/strong\u003e: Define custom content types for audio transcription, ensuring compatibility with diverse audio sources and unlocking smoother, more accurate transcriptions in advanced setups.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLDAP Group Synchronization (Experimental)\u003c/strong\u003e: Automatically sync user groups from your LDAP directory directly into Open WebUI for seamless enterprise access management—simplifies identity integration and governance across your organization.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eOpenTelemetry Metrics via OTLP Exporter (Experimental)\u003c/strong\u003e: Gain enterprise-grade analytics and monitor your AI usage in real time with experimental OpenTelemetry Metrics support—connect to any OTLP-compatible backend for instant insights into performance, load, and user interactions.\u003c/li\u003e\n\u003cli\u003e🕰️ \u003cstrong\u003eSee User Message Timestamps on Hover (Chat Bubble UI)\u003c/strong\u003e: Effortlessly check when any user message was sent by hovering over it in Chat Bubble mode—no more switching screens or digging through logs for context.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLeaderboard Sorting Options\u003c/strong\u003e: Sort the leaderboard directly in the UI for a clearer, more actionable view of top performers, models, or tools—making analysis and recognition quick and easy for teams.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eEvaluation Details Modal in Feedbacks and Leaderboard\u003c/strong\u003e: Dive deeper with new modals that display detailed evaluation information when reviewing feedbacks and leaderboard rankings—accelerates learning, progress tracking, and quality improvement.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSupport for Multiple Pages in External Document Loaders\u003c/strong\u003e: Effortlessly extract and work with content spanning multiple pages in external documents, giving you complete flexibility for in-depth research and document workflows.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eNew Accessibility Enhancements Across the Interface\u003c/strong\u003e: Benefit from significant accessibility improvements—tab navigation, ARIA roles/labels, better high-contrast text/modes, accessible modals, and more—making Open WebUI more usable and equitable for everyone, including those using assistive technologies.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePerformance \u0026amp; Stability Upgrades Across Frontend and Backend\u003c/strong\u003e: Enjoy a smoother, more reliable experience with numerous behind-the-scenes optimizations and refactoring on both frontend and backend—resulting in faster load times, fewer errors, and even greater stability throughout your workflows.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eUpdated and Expanded Localizations\u003c/strong\u003e: Enjoy improved, up-to-date translations for Finnish, German (now with model pinning features), Korean, Russian, Simplified Chinese, Spanish, and more—making every interaction smoother, clearer, and more intuitive for international users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🦾 \u003cstrong\u003eOllama Error Messages More Descriptive\u003c/strong\u003e: Receive clearer, more actionable error messages when something goes wrong with Ollama models—making troubleshooting and user support faster and more effective.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Webloader Now Works as Expected\u003c/strong\u003e: Resolved an issue where the \u0026quot;bypass webloader\u0026quot; feature failed to function correctly, ensuring web search bypasses operate smoothly and reliably for lighter, faster query results.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003ePrevent Redundant Documents in Citation List\u003c/strong\u003e: The expanded citation list no longer shows duplicate documents, offering a cleaner, easier-to-digest reference experience when reviewing sources in knowledge and research workflows.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eTrusted Header Email Matching is Now Case-Insensitive\u003c/strong\u003e: Fixed a critical authentication issue where email case sensitivity could cause secure headers to mismatch, ensuring robust, seamless login and session management in all environments.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eDirect Tool Server Input Accepts Empty Strings\u003c/strong\u003e: You can now submit direct tool server commands without unexpected errors when passing empty-string values, improving integration and automation efficiency.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eCitation Page Number for Page 1 is Now Displayed\u003c/strong\u003e: Corrected an oversight where references for page 1 documents were missing the page number; citations are now always accurate and fully visible.\u003c/li\u003e\n\u003cli\u003e📒 \u003cstrong\u003eNotes Access Restored\u003c/strong\u003e: Fixed an issue where some users could not access their notes—everyone can now view and manage their notes reliably, ensuring seamless documentation and workflow continuity.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eOAuth Callback Double-Slash Issue Resolved\u003c/strong\u003e: Fixed rare cases where an extra slash in OAuth callbacks caused failed logins or redirects, making third-party login integrations more reliable.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eDedicated Permission for System Prompts\u003c/strong\u003e: System prompt access is now controlled by its own specific permission instead of being grouped with general chat controls, empowering admins with finer-grained management over who can view or modify system prompts for enhanced security and workflow customization.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eYouTube Transcript API and python-pptx Updated\u003c/strong\u003e: Enjoy better performance, reliability, and broader compatibility thanks to underlying library upgrades—less friction with media-rich and presentation workflows.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eConsole Logging Disabled in Production\u003c/strong\u003e: All 'console.log' and 'console.debug' statements are now disabled in production, guaranteeing improved security and cleaner browser logs for end users by removing extraneous technical output.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eSelector Model Item Menu\u003c/strong\u003e: Each model in the selector now features a menu where you can easily pin/unpin to the sidebar and copy a direct link—simplifying collaboration and staying organized in even the busiest environments.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eReliable Stop for Ongoing Chats in Multi-Replica Setups\u003c/strong\u003e: Stopping or cancelling an in-progress chat now works reliably even in clustered deployments—ensuring every user can interrupt AI output at any time, no matter your scale.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003e'Think' Parameter for Ollama Models\u003c/strong\u003e: Leverage new 'think' parameter support for Ollama—giving you advanced control over AI reasoning process and further tuning model behavior for your unique use cases.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003ePicture Description Modes for Docling\u003c/strong\u003e: Customize how images are described/extracted by Docling Loader for smarter, more detailed, and workflow-tailored image understanding in your document pipelines.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eSettings Modal Deep Linking\u003c/strong\u003e: Every tab in Settings now has its own route—making direct navigation and sharing of precise settings faster and more intuitive.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eAudio HTML Component Token\u003c/strong\u003e: Easily embed and play audio directly in your chats, improving voice-based workflows and making audio content instantly accessible and manageable from any conversation.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eSupport for Secret Key File\u003c/strong\u003e: Now you can specify 'WEBUI_SECRET_KEY_FILE' for more secure and flexible key management—ideal for advanced deployments and tighter security standards.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b5f4c85bb196c16a775802907aedd87366f58b0f\"\u003e\u003ccode\u003eb5f4c85\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15014\"\u003e#15014\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/340d9820b8122035258d6931cd22f1be0a716c74\"\u003e\u003ccode\u003e340d982\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/597709c64c5f09ae8c6f069ed8e6f5a09cd8ed35\"\u003e\u003ccode\u003e597709c\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/84fd41e6eff8ff301d1224936898fce196ccb6b6\"\u003e\u003ccode\u003e84fd41e\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/3917b04ed3554d776cdbdd97b25be619ff989a8a\"\u003e\u003ccode\u003e3917b04\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b6ea043d18930f9d32382708aa58d9c44803979b\"\u003e\u003ccode\u003eb6ea043\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b082a7edbe9f33632c5959928fbd3aa21c5817be\"\u003e\u003ccode\u003eb082a7e\u003c/code\u003e\u003c/a\u003e enh: allow iframe in content\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/72df23ed79b74036480ea45735350a04b6c6456b\"\u003e\u003ccode\u003e72df23e\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/11476eb6eee96d98747eb978b39f8a620db1a849\"\u003e\u003ccode\u003e11476eb\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7096baff1b09e9fcaf498ffc626bf44dd65de162\"\u003e\u003ccode\u003e7096baf\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15021\"\u003e#15021\u003c/a\u003e from rgaricano/dev\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.15\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=0.6.15)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/68","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/68","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/68/packages"},{"uuid":"3134676705","node_id":"PR_kwDOM-FVBM6Z61_G","number":67,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to 0.6.14 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-06-16T20:46:39.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-06-10T19:46:22.000Z","updated_at":"2025-06-16T20:46:39.000Z","time_to_close":522017,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"0.6.14","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to 0.6.14.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.14\u003c/h2\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eSelector Model Item Menu\u003c/strong\u003e: Each model in the selector now features a menu where you can easily pin/unpin to the sidebar and copy a direct link—simplifying collaboration and staying organized in even the busiest environments.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eReliable Stop for Ongoing Chats in Multi-Replica Setups\u003c/strong\u003e: Stopping or cancelling an in-progress chat now works reliably even in clustered deployments—ensuring every user can interrupt AI output at any time, no matter your scale.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003e'Think' Parameter for Ollama Models\u003c/strong\u003e: Leverage new 'think' parameter support for Ollama—giving you advanced control over AI reasoning process and further tuning model behavior for your unique use cases.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003ePicture Description Modes for Docling\u003c/strong\u003e: Customize how images are described/extracted by Docling Loader for smarter, more detailed, and workflow-tailored image understanding in your document pipelines.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eSettings Modal Deep Linking\u003c/strong\u003e: Every tab in Settings now has its own route—making direct navigation and sharing of precise settings faster and more intuitive.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eAudio HTML Component Token\u003c/strong\u003e: Easily embed and play audio directly in your chats, improving voice-based workflows and making audio content instantly accessible and manageable from any conversation.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eSupport for Secret Key File\u003c/strong\u003e: Now you can specify 'WEBUI_SECRET_KEY_FILE' for more secure and flexible key management—ideal for advanced deployments and tighter security standards.\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eClarity When Cloning Prompts\u003c/strong\u003e: Cloned workspace prompts are clearly labelled with \u0026quot;(Clone)\u0026quot; and IDs have \u0026quot;-clone\u0026quot;, keeping your prompt library organized and preventing accidental overwrites.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eDedicated User Role Edit Modal\u003c/strong\u003e: Updating user roles now reliably opens a dedicated edit user modal instead of cycling through roles—making it safer and more clear to manage team permissions.\u003c/li\u003e\n\u003cli\u003e🏞️ \u003cstrong\u003eBetter Handling \u0026amp; Storage of Interpreter-Generated Images\u003c/strong\u003e: Code interpreter-generated images are now centrally stored and reliably loaded from the database or cloud storage, ensuring your artifacts are always available.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003ePinecone \u0026amp; Vector Search Optimizations\u003c/strong\u003e: Applied latest best practices from Pinecone for smarter timeouts, intelligent retry control, improved connection pooling, faster DNS, and concurrent batch handling—giving you more reliable, faster document search and RAG performance without manual tweaks.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eOllama Advanced Parameters Unified\u003c/strong\u003e: 'keep_alive' and 'format' options are now integrated into the advanced params section—edit everything from the model editor for flexible model control.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eCUDA 12.6 Docker Image Support\u003c/strong\u003e: Deploy to NVIDIA GPUs with capability 7.0 and below (e.g., V100, GTX1080) via new cuda126 image—broadening your hardware options for scalable AI workloads.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eExperimental Table-Level PGVector Data Encryption\u003c/strong\u003e: Activate pgcrypto encryption support for pgvector to secure your vector search table contents, giving organizations enhanced compliance and data protection—perfect for enterprise or regulated environments.\u003c/li\u003e\n\u003cli\u003e👁 \u003cstrong\u003eAccessibility Upgrades Across Interface\u003c/strong\u003e: Chat buttons and close controls are now labelled and structured for optimal accessibility support, ensuring smoother operation with assistive technologies.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eHigh-Contrast Mode Expansions\u003c/strong\u003e: High-contrast accessibility mode now also applies to menu items, tabs, and search input fields, offering a more readable experience for all users.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTooltip \u0026amp; Translation Clarity\u003c/strong\u003e: Improved translation and tooltip clarity, especially over radio buttons, making the UI more understandable for all users.\u003c/li\u003e\n\u003cli\u003e🔠 \u003cstrong\u003eGlobal Localization \u0026amp; Translation Improvements\u003c/strong\u003e: Hefty upgrades to Traditional Chinese, Simplified Chinese, Hebrew, Russian, Irish, German, and Danish translation packs—making the platform feel native and intuitive for even more users worldwide.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGeneral Backend Stability \u0026amp; Security Enhancements\u003c/strong\u003e: Refined numerous backend routines to minimize memory use, improve performance, and streamline integration with external APIs—making the entire platform more robust and secure for daily work.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷 \u003cstrong\u003eFeedback Score Display Improved\u003c/strong\u003e: Addressed overflow and visibility issues with feedback scores for more readable and accessible evaluations.\u003c/li\u003e\n\u003cli\u003e🗂 \u003cstrong\u003eAdmin Settings Model Edits Apply Immediately\u003c/strong\u003e: Changes made in the Model Editor within Admin Settings now take effect instantly, eliminating confusion during model management.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eAssigned Tools Update Instantly on New Chats\u003c/strong\u003e: Models assigned with specific tools now consistently update and are available in every new chat—making tool workflows more predictable and robust.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eDocument Settings Saved Only on User Action\u003c/strong\u003e: Document settings now save only when you press the Save button, reducing accidental changes and ensuring greater control.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eVoice Recording on Older iOS Devices Restored\u003c/strong\u003e: Voice input is now fully functional on older iOS devices, keeping voice workflows accessible to all users.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eTrusted Email Header Session Security\u003c/strong\u003e: User sessions now strictly verify the trusted email header matches the logged-in user's email, ensuring secure authentication and preventing accidental session switching.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConsistent User Signout on Email Mismatch\u003c/strong\u003e: When the trusted email in the header changes, you will now be properly signed out and redirected, safeguarding your session's integrity.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eGeneral Error \u0026amp; Content Validation Improvements\u003c/strong\u003e: Smarter error handling means clearer messages and fewer unnecessary retries—making batch uploads, document handling, and knowledge indexing more resilient.\u003c/li\u003e\n\u003cli\u003e🕵️ \u003cstrong\u003eBetter Feedback on Chat Title Edits\u003c/strong\u003e: Error messages now show clearly if problems occur while editing chat titles.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eSelector Model Item Menu\u003c/strong\u003e: Each model in the selector now features a menu where you can easily pin/unpin to the sidebar and copy a direct link—simplifying collaboration and staying organized in even the busiest environments.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eReliable Stop for Ongoing Chats in Multi-Replica Setups\u003c/strong\u003e: Stopping or cancelling an in-progress chat now works reliably even in clustered deployments—ensuring every user can interrupt AI output at any time, no matter your scale.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003e'Think' Parameter for Ollama Models\u003c/strong\u003e: Leverage new 'think' parameter support for Ollama—giving you advanced control over AI reasoning process and further tuning model behavior for your unique use cases.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003ePicture Description Modes for Docling\u003c/strong\u003e: Customize how images are described/extracted by Docling Loader for smarter, more detailed, and workflow-tailored image understanding in your document pipelines.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eSettings Modal Deep Linking\u003c/strong\u003e: Every tab in Settings now has its own route—making direct navigation and sharing of precise settings faster and more intuitive.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eAudio HTML Component Token\u003c/strong\u003e: Easily embed and play audio directly in your chats, improving voice-based workflows and making audio content instantly accessible and manageable from any conversation.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eSupport for Secret Key File\u003c/strong\u003e: Now you can specify 'WEBUI_SECRET_KEY_FILE' for more secure and flexible key management—ideal for advanced deployments and tighter security standards.\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eClarity When Cloning Prompts\u003c/strong\u003e: Cloned workspace prompts are clearly labelled with \u0026quot;(Clone)\u0026quot; and IDs have \u0026quot;-clone\u0026quot;, keeping your prompt library organized and preventing accidental overwrites.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eDedicated User Role Edit Modal\u003c/strong\u003e: Updating user roles now reliably opens a dedicated edit user modal instead of cycling through roles—making it safer and more clear to manage team permissions.\u003c/li\u003e\n\u003cli\u003e🏞️ \u003cstrong\u003eBetter Handling \u0026amp; Storage of Interpreter-Generated Images\u003c/strong\u003e: Code interpreter-generated images are now centrally stored and reliably loaded from the database or cloud storage, ensuring your artifacts are always available.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003ePinecone \u0026amp; Vector Search Optimizations\u003c/strong\u003e: Applied latest best practices from Pinecone for smarter timeouts, intelligent retry control, improved connection pooling, faster DNS, and concurrent batch handling—giving you more reliable, faster document search and RAG performance without manual tweaks.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eOllama Advanced Parameters Unified\u003c/strong\u003e: 'keep_alive' and 'format' options are now integrated into the advanced params section—edit everything from the model editor for flexible model control.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eCUDA 12.6 Docker Image Support\u003c/strong\u003e: Deploy to NVIDIA GPUs with capability 7.0 and below (e.g., V100, GTX1080) via new cuda126 image—broadening your hardware options for scalable AI workloads.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eExperimental Table-Level PGVector Data Encryption\u003c/strong\u003e: Activate pgcrypto encryption support for pgvector to secure your vector search table contents, giving organizations enhanced compliance and data protection—perfect for enterprise or regulated environments.\u003c/li\u003e\n\u003cli\u003e👁 \u003cstrong\u003eAccessibility Upgrades Across Interface\u003c/strong\u003e: Chat buttons and close controls are now labelled and structured for optimal accessibility support, ensuring smoother operation with assistive technologies.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eHigh-Contrast Mode Expansions\u003c/strong\u003e: High-contrast accessibility mode now also applies to menu items, tabs, and search input fields, offering a more readable experience for all users.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTooltip \u0026amp; Translation Clarity\u003c/strong\u003e: Improved translation and tooltip clarity, especially over radio buttons, making the UI more understandable for all users.\u003c/li\u003e\n\u003cli\u003e🔠 \u003cstrong\u003eGlobal Localization \u0026amp; Translation Improvements\u003c/strong\u003e: Hefty upgrades to Traditional Chinese, Simplified Chinese, Hebrew, Russian, Irish, German, and Danish translation packs—making the platform feel native and intuitive for even more users worldwide.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGeneral Backend Stability \u0026amp; Security Enhancements\u003c/strong\u003e: Refined numerous backend routines to minimize memory use, improve performance, and streamline integration with external APIs—making the entire platform more robust and secure for daily work.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷 \u003cstrong\u003eFeedback Score Display Improved\u003c/strong\u003e: Addressed overflow and visibility issues with feedback scores for more readable and accessible evaluations.\u003c/li\u003e\n\u003cli\u003e🗂 \u003cstrong\u003eAdmin Settings Model Edits Apply Immediately\u003c/strong\u003e: Changes made in the Model Editor within Admin Settings now take effect instantly, eliminating confusion during model management.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eAssigned Tools Update Instantly on New Chats\u003c/strong\u003e: Models assigned with specific tools now consistently update and are available in every new chat—making tool workflows more predictable and robust.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eDocument Settings Saved Only on User Action\u003c/strong\u003e: Document settings now save only when you press the Save button, reducing accidental changes and ensuring greater control.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eVoice Recording on Older iOS Devices Restored\u003c/strong\u003e: Voice input is now fully functional on older iOS devices, keeping voice workflows accessible to all users.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eTrusted Email Header Session Security\u003c/strong\u003e: User sessions now strictly verify the trusted email header matches the logged-in user's email, ensuring secure authentication and preventing accidental session switching.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConsistent User Signout on Email Mismatch\u003c/strong\u003e: When the trusted email in the header changes, you will now be properly signed out and redirected, safeguarding your session's integrity.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eGeneral Error \u0026amp; Content Validation Improvements\u003c/strong\u003e: Smarter error handling means clearer messages and fewer unnecessary retries—making batch uploads, document handling, and knowledge indexing more resilient.\u003c/li\u003e\n\u003cli\u003e🕵️ \u003cstrong\u003eBetter Feedback on Chat Title Edits\u003c/strong\u003e: Error messages now show clearly if problems occur while editing chat titles.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/63256136ef8322210c01c2bb322097d1ccfb8c6f\"\u003e\u003ccode\u003e6325613\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14675\"\u003e#14675\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/fd8cdb383c9ba37010c636e3937a13ab94044a94\"\u003e\u003ccode\u003efd8cdb3\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ab42a192e69140e0a417d669d166183ff7d9567b\"\u003e\u003ccode\u003eab42a19\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/adab4dbf218bf08ee22a05e658726a76871b9a05\"\u003e\u003ccode\u003eadab4db\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/c14160d73af5375048fd84abe7fb153c03368cbf\"\u003e\u003ccode\u003ec14160d\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14845\"\u003e#14845\u003c/a\u003e from itk-dev/feature/accessibility-aria-label-close...\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a7330d97da59d0280ba95374d278df91af5620cb\"\u003e\u003ccode\u003ea7330d9\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b39d33cefbb58f35d29d4de9b743ba8637dfc2d5\"\u003e\u003ccode\u003eb39d33c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d2e7feea86b4fdbc0b4465133b3da664b7d33b70\"\u003e\u003ccode\u003ed2e7fee\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a018140c7d2b89b8fe02e5c0cf87cb59462f6df6\"\u003e\u003ccode\u003ea018140\u003c/code\u003e\u003c/a\u003e refac: admin settings models\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9931ccef1eb6448ea8df7949ca407acb040e428f\"\u003e\u003ccode\u003e9931cce\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.14\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=0.6.14)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/67","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/67","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/67/packages"},{"uuid":"2558734612","node_id":"PR_kwDONjNt7s6YgzEU","number":5,"state":"open","title":"Bump open-webui/open-webui from `3039364` to `4583b43`","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-06-01T22:51:30.000Z","updated_at":"2025-06-01T22:51:31.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"`3039364`","new_version":"`4583b43`","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from `3039364` to `4583b43`.\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch1\u003eChangelog\u003c/h1\u003e\n\u003cp\u003eAll notable changes to this project will be documented in this file.\u003c/p\u003e\n\u003cp\u003eThe format is based on \u003ca href=\"https://keepachangelog.com/en/1.1.0/\"\u003eKeep a Changelog\u003c/a\u003e,\nand this project adheres to \u003ca href=\"https://semver.org/spec/v2.0.0.html\"\u003eSemantic Versioning\u003c/a\u003e.\u003c/p\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRobust Message Handling on Chat Load\u003c/strong\u003e: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCorrect Prompt Access Control\u003c/strong\u003e: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eOpen WebUI-Specific Params No Longer Sent to Models\u003c/strong\u003e: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmitted—restoring predictable, error-free model operation.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eRefined Memory Error Handling\u003c/strong\u003e: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your session—resulting in a more reliable, worry-free experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.11] - 2025-05-27\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟢 \u003cstrong\u003eOllama Model Status Indicator in Model Selector\u003c/strong\u003e: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003eSee full diff in \u003ca href=\"https://github.com/open-webui/open-webui/commits\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=main\u0026new-version=main)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/ArloL/open-webui-runner/pull/5","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArloL%2Fopen-webui-runner/issues/5","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/5/packages"},{"uuid":"2555504799","node_id":"PR_kwDOM-FVBM6YUeif","number":66,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to v0.6.13 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-06-10T19:46:24.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-05-30T19:21:26.000Z","updated_at":"2025-06-10T19:46:24.000Z","time_to_close":951898,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"v0.6.13","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to v0.6.13.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.13\u003c/h2\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRobust Message Handling on Chat Load\u003c/strong\u003e: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCorrect Prompt Access Control\u003c/strong\u003e: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eOpen WebUI-Specific Params No Longer Sent to Models\u003c/strong\u003e: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmitted—restoring predictable, error-free model operation.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eRefined Memory Error Handling\u003c/strong\u003e: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your session—resulting in a more reliable, worry-free experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.12\u003c/h2\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:\u003c/p\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRobust Message Handling on Chat Load\u003c/strong\u003e: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCorrect Prompt Access Control\u003c/strong\u003e: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eOpen WebUI-Specific Params No Longer Sent to Models\u003c/strong\u003e: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmitted—restoring predictable, error-free model operation.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eRefined Memory Error Handling\u003c/strong\u003e: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your session—resulting in a more reliable, worry-free experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.11] - 2025-05-27\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟢 \u003cstrong\u003eOllama Model Status Indicator in Model Selector\u003c/strong\u003e: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eUnload Ollama Model Directly from Model Selector\u003c/strong\u003e: Easily release memory and resources by unloading any loaded Ollama model right in the model selector—streamline hardware management without switching pages.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eUser-Configurable Speech-to-Text Language Setting\u003c/strong\u003e: Improve transcription accuracy by letting individual users explicitly set their preferred STT language in their settings—ideal for multilingual teams and clear audio capture.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGranular Audio Playback Speed Control\u003c/strong\u003e: Instead of just presets, you can now choose granular audio speed using a numeric input, giving you complete control over playback pace in transcriptions and media reviews.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eGZip, Brotli, ZStd Compression Middleware\u003c/strong\u003e: Enjoy significantly faster page loads and reduced bandwidth usage with new server-side compression—giving users a snappier, more efficient experience.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eConfigurable Weight for BM25 in Hybrid Search\u003c/strong\u003e: Fine-tune search relevance by adjusting the weight for BM25 inside hybrid search from the UI, letting you tailor knowledge search results to your workflow.\u003c/li\u003e\n\u003cli\u003e🧪 \u003cstrong\u003eBypass File Creation with CTRL + SHIFT + V\u003c/strong\u003e: When “Paste Large Text as File” is enabled, use CTRL + SHIFT + V to skip the file creation dialog and instantly upload text as a file—perfect for rapid document prep.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Web Loader in Web Search\u003c/strong\u003e: Choose to bypass web content loading and use snippets directly in web search for faster, more reliable results when page loads are slow or blocked.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/53764fe64884da147359e54ed6d9607fe57f1600\"\u003e\u003ccode\u003e53764fe\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14486\"\u003e#14486\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/235489cfc55116e805ae8a3ee6a84efdcc1e40de\"\u003e\u003ccode\u003e235489c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b2befd486fde81f49f10728affb139a96bd794d7\"\u003e\u003ccode\u003eb2befd4\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9306ae597238d956a9613f74e530dd61125e0cfa\"\u003e\u003ccode\u003e9306ae5\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/036ce12dd94c61f7f8751eb37afa3476c3068679\"\u003e\u003ccode\u003e036ce12\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d6c3f93cfdacaab4340b7892ce2f0cb799c62cc2\"\u003e\u003ccode\u003ed6c3f93\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14509\"\u003e#14509\u003c/a\u003e from r0mdau/fix/audio-format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b12a493fe5248d51ad755586e8a306d820ce9770\"\u003e\u003ccode\u003eb12a493\u003c/code\u003e\u003c/a\u003e fix: only trust codec_name for audio conversion\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f4827f0c18d9df2c3cc5ebdb26ebe04148c3c8ae\"\u003e\u003ccode\u003ef4827f0\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e1e2c096e298dd6bab5921ed1dd62d42f317f576\"\u003e\u003ccode\u003ee1e2c09\u003c/code\u003e\u003c/a\u003e refac: PLEASE follow existing convention\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ff353578dbf28040501e2cfe32add8a914059ddc\"\u003e\u003ccode\u003eff35357\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14370\"\u003e#14370\u003c/a\u003e from daw/feat/add-azure-openai-embeddings-option\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.13\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=v0.6.13)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/66","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/66","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/66/packages"},{"uuid":"2553068937","node_id":"PR_kwDOM-FVBM6YLL2J","number":64,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to v0.6.12 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-05-30T19:21:28.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-05-29T19:37:05.000Z","updated_at":"2025-05-30T19:21:28.000Z","time_to_close":85463,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"v0.6.12","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to v0.6.12.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.12\u003c/h2\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:\n\u003ca href=\"https://github.com/TiancongLx\"\u003e\u003ccode\u003e@​TiancongLx\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/SadmL\"\u003e\u003ccode\u003e@​SadmL\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Hisma\"\u003e\u003ccode\u003e@​Hisma\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Zyfax\"\u003e\u003ccode\u003e@​Zyfax\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/qingchunnh\"\u003e\u003ccode\u003e@​qingchunnh\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/NotYuSheng\"\u003e\u003ccode\u003e@​NotYuSheng\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/torisetxd\"\u003e\u003ccode\u003e@​torisetxd\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/hurxxxx\"\u003e\u003ccode\u003e@​hurxxxx\u003c/code\u003e\u003c/a\u003e\u003c/p\u003e\n\u003ch2\u003eSponsors 🙌\u003c/h2\u003e\n\u003cp\u003e🚀 We'd like to extend a heartfelt thank you to our amazing sponsors for their generous support (Note: We've excluded private sponsors from this list. If you'd like to get featured here, feel free to reach out to us!)\u003c/p\u003e\n\u003ch4\u003eEmerald\u003c/h4\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003en8n\u003c/strong\u003e \u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWarp\u003c/strong\u003e \u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003ca href=\"https://github.com/amd\"\u003e\u003ccode\u003e@​amd\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/agency-agency\"\u003e\u003ccode\u003e@​agency-agency\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/roosi-gmbh\"\u003e\u003ccode\u003e@​roosi-gmbh\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Unsupervisedcom\"\u003e\u003ccode\u003e@​Unsupervisedcom\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/feddersen-group\"\u003e\u003ccode\u003e@​feddersen-group\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/SRKConsulting\"\u003e\u003ccode\u003e@​SRKConsulting\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/mushmax\"\u003e\u003ccode\u003e@​mushmax\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/rndmcnlly\"\u003e\u003ccode\u003e@​rndmcnlly\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/icanbwell\"\u003e\u003ccode\u003e@​icanbwell\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/blogic-cz\"\u003e\u003ccode\u003e@​blogic-cz\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Krambu-Travis\"\u003e\u003ccode\u003e@​Krambu-Travis\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/GenieDev101\"\u003e\u003ccode\u003e@​GenieDev101\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/PortlandKyGuy\"\u003e\u003ccode\u003e@​PortlandKyGuy\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/CubicleGangster\"\u003e\u003ccode\u003e@​CubicleGangster\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/GitDatamind\"\u003e\u003ccode\u003e@​GitDatamind\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/TOWaB\"\u003e\u003ccode\u003e@​TOWaB\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/TheZigGroup\"\u003e\u003ccode\u003e@​TheZigGroup\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Classic298\"\u003e\u003ccode\u003e@​Classic298\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/comet-ml\"\u003e\u003ccode\u003e@​comet-ml\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/chAyubTahir\"\u003e\u003ccode\u003e@​chAyubTahir\u003c/code\u003e\u003c/a\u003e\u003c/p\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.11] - 2025-05-27\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟢 \u003cstrong\u003eOllama Model Status Indicator in Model Selector\u003c/strong\u003e: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eUnload Ollama Model Directly from Model Selector\u003c/strong\u003e: Easily release memory and resources by unloading any loaded Ollama model right in the model selector—streamline hardware management without switching pages.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eUser-Configurable Speech-to-Text Language Setting\u003c/strong\u003e: Improve transcription accuracy by letting individual users explicitly set their preferred STT language in their settings—ideal for multilingual teams and clear audio capture.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGranular Audio Playback Speed Control\u003c/strong\u003e: Instead of just presets, you can now choose granular audio speed using a numeric input, giving you complete control over playback pace in transcriptions and media reviews.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eGZip, Brotli, ZStd Compression Middleware\u003c/strong\u003e: Enjoy significantly faster page loads and reduced bandwidth usage with new server-side compression—giving users a snappier, more efficient experience.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eConfigurable Weight for BM25 in Hybrid Search\u003c/strong\u003e: Fine-tune search relevance by adjusting the weight for BM25 inside hybrid search from the UI, letting you tailor knowledge search results to your workflow.\u003c/li\u003e\n\u003cli\u003e🧪 \u003cstrong\u003eBypass File Creation with CTRL + SHIFT + V\u003c/strong\u003e: When “Paste Large Text as File” is enabled, use CTRL + SHIFT + V to skip the file creation dialog and instantly upload text as a file—perfect for rapid document prep.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Web Loader in Web Search\u003c/strong\u003e: Choose to bypass web content loading and use snippets directly in web search for faster, more reliable results when page loads are slow or blocked.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eEnvironment Variable: WEBUI_AUTH_TRUSTED_GROUPS_HEADER\u003c/strong\u003e: Now sync and manage user groups directly via trusted HTTP header, unlocking smoother single sign-on and identity integrations for organizations.\u003c/li\u003e\n\u003cli\u003e🏢 \u003cstrong\u003eWorkspace Models Visibility Controls\u003c/strong\u003e: You can now hide workspace-level models from both the model selector and shared environments—keep your team focused and reduce clutter from rarely-used endpoints.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eCopy Model Link\u003c/strong\u003e: You can now copy a direct link to any model—including those hidden from the selector—making sharing and onboarding others more seamless.\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eLoad Function Directly from URL\u003c/strong\u003e: Simplify custom function management—just paste any GitHub function URL into Open WebUI and import new functions in seconds.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eCustom Name/Description for External Tool Servers\u003c/strong\u003e: Personalize and clarify external tool servers by assigning custom names and descriptions, making it easier to manage integrations in large-scale workspaces.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eCustom OpenAPI JSON URL Support for Tool Servers\u003c/strong\u003e: Supports specifying any custom OpenAPI JSON URL, unlocking more flexible integration with any backend for tool calls.\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eSource Field Now Displays in Non-Streaming Responses with Attachments\u003c/strong\u003e: When files or knowledge are attached, the \u0026quot;source\u0026quot; field now appears for all responses, even in non-streaming mode—enabling improved citation workflow.\u003c/li\u003e\n\u003cli\u003e🎛 \u003cstrong\u003ePinned Chats\u003c/strong\u003e: Reduced payload size on pinned chat requests—leading to faster load times and less data usage, especially on busy warehouses.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eImport/Export Default Prompt Suggestions\u003c/strong\u003e: Enjoy one-click import/export of prompt suggestions, making it much easier to share, reuse, and manage best practices across teams or deployments.\u003c/li\u003e\n\u003cli\u003e🍰 \u003cstrong\u003eBanners Now Sortable from Admin Settings\u003c/strong\u003e: Quickly re-order or prioritize banners, letting you highlight the most critical info for your team.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eAdvanced Chat Parameters—Clearer Ollama Support Labels\u003c/strong\u003e: Parameters and advanced settings now explicitly indicate if they are Ollama-specific, reducing confusion and improving setup accuracy.\u003c/li\u003e\n\u003cli\u003e🤏 \u003cstrong\u003eScroll Bar Thumb Improved for Better Visibility\u003c/strong\u003e: Enhanced scrollbar styling makes navigation more accessible and visually intuitive.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eModal Redesign for Archived and User Chat Listings\u003c/strong\u003e: Clean, modern modal interface for browsing archived and user-specific chats makes locating conversations faster and more pleasant.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eAdd/Edit Memory Modal UX\u003c/strong\u003e: Memory modals are now larger and have resizable input fields, supporting easier editing of long or complex memory content.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eTranslation \u0026amp; Localization Enhancements\u003c/strong\u003e: Major upgrades to Chinese (Simplified \u0026amp; Traditional), Korean, Russian, German, Danish, Finnish—not just fixing typos, but consistency, tone, and terminology for a more natural native-language experience.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGeneral Backend Stability \u0026amp; Security Enhancements\u003c/strong\u003e: Various backend refinements ensure a more resilient, reliable, and secure platform for smoother operation and peace of mind.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ba0088f39b7a093920b142a5172554686f24df60\"\u003e\u003ccode\u003eba0088f\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14441\"\u003e#14441\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/661625f3622e006befb79953705ac95dbc8e3ec1\"\u003e\u003ccode\u003e661625f\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/30b7ab3591645d13675158423c5f0cd183fb8116\"\u003e\u003ccode\u003e30b7ab3\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7dc7d5c028a662c618f09c50e01ccf5b1833a77f\"\u003e\u003ccode\u003e7dc7d5c\u003c/code\u003e\u003c/a\u003e refac: PLEASE FOLLOW EXISTING CONVENTION\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2c31f5c72540f8cfb9343f1e61885785ee5db310\"\u003e\u003ccode\u003e2c31f5c\u003c/code\u003e\u003c/a\u003e doc: readme\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a6864db8ece88b9dae743445b290fd03e61e035b\"\u003e\u003ccode\u003ea6864db\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/21f85e63bf26877a62be9a2b6a04b3f4b35b6436\"\u003e\u003ccode\u003e21f85e6\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9220afe7b315b53f9afc73756e08d5041c5eedf7\"\u003e\u003ccode\u003e9220afe\u003c/code\u003e\u003c/a\u003e feat: custom advanced params\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/bb4115fa0edbb610f1d3f98c2a02e070579cfdca\"\u003e\u003ccode\u003ebb4115f\u003c/code\u003e\u003c/a\u003e refac: allow all params\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/551597b9cc09df401ead368f731898052cc6b8cc\"\u003e\u003ccode\u003e551597b\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.12\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=v0.6.12)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/64","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/64","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/64/packages"}],"issue_packages":[{"old_version":"v0.8.8-slim","new_version":"v0.8.11-slim","update_type":"patch","path":null,"pr_created_at":"2026-03-26T07:15:19.000Z","version_change":"v0.8.8-slim → v0.8.11-slim","issue":{"uuid":"4141310856","node_id":"PR_kwDOPIpjyc7Nm73m","number":36,"state":"closed","title":"Bump open-webui/open-webui from v0.8.8-slim to v0.8.11-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-03-27T07:16:24.000Z","author_association":null,"state_reason":null,"created_at":"2026-03-26T07:15:19.000Z","updated_at":"2026-03-27T07:16:26.000Z","time_to_close":86465,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.8.8-slim","new_version":"v0.8.11-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.8.8-slim to v0.8.11-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.11\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔀 \u003cstrong\u003eResponses API streaming improvements.\u003c/strong\u003e The OpenAI proxy now properly handles tool call streaming and re-invocations in the Responses API, preventing duplicate tool calls and preserving output during model re-invocations. \u003ca href=\"https://github.com/open-webui/open-webui/commit/93415a48e8893139db13d02d0a6d24e8604a2ac5\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f8b3a32caf00dad76687fd8fe698b86f304f3997\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/2ae47cf20057e92a83fd618b938f3ee9bb124e5b\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/adcbba34f8bbfbab3e4041269a084f2b71c076d9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔀 \u003cstrong\u003eResponses API stateful sessions.\u003c/strong\u003e Administrators can now enable experimental stateful session support via the ENABLE_RESPONSES_API_STATEFUL environment variable, allowing compatible backends to store responses server-side with previous_response_id anchoring for improved multi-turn conversations. \u003ca href=\"https://github.com/open-webui/open-webui/commit/dfc2dc2c0bd298cb4bfcf212ef11223586aa54f1\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eFile viewing pagination.\u003c/strong\u003e The view_file and view_knowledge_file tools now support pagination with offset and max_chars parameters, allowing models to read large files in chunks. \u003ca href=\"https://github.com/open-webui/open-webui/commit/5d7766e1b6f7ca7749c5a5a780d7b1bb2da28a2f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗺️ \u003cstrong\u003eKnowledge search scoping.\u003c/strong\u003e The search_knowledge_files tool now respects model-attached knowledge, searching only within attached knowledge bases and files when available. \u003ca href=\"https://github.com/open-webui/open-webui/commit/0f0ba7dadd043460d205477fd3b57556aa970847\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTool HTML embed context.\u003c/strong\u003e Tools can now return custom context alongside HTML embeds by using a tuple format, providing the LLM with actionable information instead of a generic message. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22691\"\u003e#22691\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eTrusted role header configuration.\u003c/strong\u003e Administrators can now configure the WEBUI_AUTH_TRUSTED_ROLE_HEADER environment variable to set user roles (admin, user, or pending) via a trusted header from their identity provider or reverse proxy. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22523\"\u003e#22523\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eOIDC authorization parameter injection.\u003c/strong\u003e Administrators can now inject extra parameters into the OIDC authorization redirect URL via the OAUTH_AUTHORIZE_PARAMS environment variable, enabling IdP pre-selection for brokers like CILogon and Keycloak. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22863\"\u003e#22863\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/69171a4c8bb7f995461b4a2feef194f112b32004\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eGoogle OAuth session persistence.\u003c/strong\u003e Administrators can now configure Google OAuth to issue refresh tokens via the GOOGLE_OAUTH_AUTHORIZE_PARAMS environment variable, preventing OAuth sessions from expiring after one hour and ensuring tools and integrations that rely on OAuth tokens remain functional. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22652\"\u003e#22652\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔌 \u003cstrong\u003eEmbed prompt confirmation.\u003c/strong\u003e Interactive tool embeds can now submit prompts to the chat without requiring same-origin access, showing a confirmation dialog for cross-origin requests to prevent abuse. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22908\"\u003e#22908\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏮 \u003cstrong\u003eTool binary response handling.\u003c/strong\u003e Tool servers can now return binary data such as images, which are properly processed and displayed in chat for both multimodal and non-multimodal models. \u003ca href=\"https://github.com/open-webui/open-webui/commit/1c25b06dca83ad491b4dc3d373b1c215a7a8fd3e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/108a019cb8e63a533250abe84f2b6f2b7c2131c4\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eSvelte upgrade performance.\u003c/strong\u003e Page and markdown rendering are now approximately 25% faster across the board, with significantly less memory usage for smoother UI interactions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22611\"\u003e#22611\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eModel and filter lookup optimization.\u003c/strong\u003e Model and filter membership lookups are now faster thanks to optimized data structure operations during model list loading. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7eae377c01f8d2de94a694b72279f769c82658cd\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eChat render throttling.\u003c/strong\u003e Chat message rendering now uses requestAnimationFrame batching to stay smooth during rapid model responses, preventing dropped frames when fast models send many events per second. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22947\"\u003e#22947\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eFunction list API optimization.\u003c/strong\u003e The functions list API now returns only essential metadata without function source code, reducing payload sizes by over 99% and making the Functions admin page load significantly faster. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22788\"\u003e#22788\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eSmoother loading animation.\u003c/strong\u003e The loading shimmer animation now looks smoother and more natural, with softer highlight colors. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22516\"\u003e#22516\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧪 \u003cstrong\u003eTerminal connection verification.\u003c/strong\u003e Users can now verify their terminal server connection is working before saving the configuration, making setup more reliable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22567\"\u003e#22567\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eChat folder emoji reset.\u003c/strong\u003e Users can now reset chat folder emojis back to the default icon using a \u0026quot;Reset to Default\u0026quot; button in the emoji picker, making it easier to revert custom icons. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22554\"\u003e#22554\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eMetrics export interval configuration.\u003c/strong\u003e Administrators can now control OpenTelemetry metrics export frequency via the OTEL_METRICS_EXPORT_INTERVAL_MILLIS environment variable, enabling cost optimization for metrics services like Grafana Cloud. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22529\"\u003e#22529\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏥 \u003cstrong\u003eReadiness probe endpoint.\u003c/strong\u003e A new /ready endpoint is now available for Kubernetes deployments, returning 200 only after startup completes and database/Redis are reachable, enabling more reliable container orchestration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22507\"\u003e#22507\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔩 \u003cstrong\u003eTool server timeout configuration.\u003c/strong\u003e Administrators can now configure a separate HTTP timeout for tool server requests via the AIOHTTP_CLIENT_TIMEOUT_TOOL_SERVER environment variable, enabling fine-tuned control over how long tool calls are allowed to take. \u003ca href=\"https://github.com/open-webui/open-webui/commit/a3238aa79f344765f5b62cb64eba71ffd001abaf\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eKnowledge file previews.\u003c/strong\u003e Knowledge base files can now be opened in a new tab directly from the file list, making it easier to view content without downloading. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22629\"\u003e#22629\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eKnowledge tool hybrid search support.\u003c/strong\u003e The built-in query_knowledge_files tool now respects hybrid search and reranking settings, matching the behavior of the middleware RAG pipeline. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a2c60d5954ecbc172d09e9955d52a07d135dcbc\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eTemporary chat folder support.\u003c/strong\u003e Temporary chats can now use folder-level system prompts and knowledge files, making them more powerful for quick explorations. \u003ca href=\"https://github.com/open-webui/open-webui/commit/adcc50d3370301afd5561e0f58ff6f3ab3750818\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📡 \u003cstrong\u003eTerminal port previews.\u003c/strong\u003e Detected ports in the File Navigator can now be previewed inline with a browser-style view, navigation controls, and an address bar, instead of only opening in a new tab. \u003ca href=\"https://github.com/open-webui/open-webui/commit/689061822173e561a153290b2bb816f4cb6f4959\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/1dc647f43b1929f5c4d1af393a90a47f56cb745e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eFile renaming.\u003c/strong\u003e Files and folders in the File Navigator can now be renamed by double-clicking or using the context menu, with Enter to confirm and Escape to cancel. \u003ca href=\"https://github.com/open-webui/open-webui/commit/637cd136c2271baf4787815bc8bc25241626a943\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧭 \u003cstrong\u003eFile Navigator navigation history.\u003c/strong\u003e The File Navigator toolbar now includes Back and Forward buttons for navigating through folder and file history, similar to a web browser. \u003ca href=\"https://github.com/open-webui/open-webui/commit/3a4b862e818c69fff6f3a3c67b50c51aa00c03e9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eDelete connection confirmations.\u003c/strong\u003e Users are now prompted with a confirmation dialog before deleting connections, preventing accidental deletions. \u003ca href=\"https://github.com/open-webui/open-webui/commit/157ff57c40bc40c53bc608828dac3779e95c2ffa\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eDocument loader fallbacks.\u003c/strong\u003e Excel and PowerPoint files can now be processed even when the unstructured package is not installed, using pandas and python-pptx as fallback loaders. \u003ca href=\"https://github.com/open-webui/open-webui/commit/6862d618ee17f95d3cae78819ed993e7fbc7e632\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eMemory management search and sort.\u003c/strong\u003e Users can now search and sort their personal memories in the Memory management modal, making it easier to find specific memories. \u003ca href=\"https://github.com/open-webui/open-webui/commit/47ab4c71d50fd631b04c95f2febb085dd0a13083\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eSBOM generation script.\u003c/strong\u003e A new script for generating CycloneDX Software Bill of Materials is now available in the scripts directory. \u003ca href=\"https://github.com/open-webui/open-webui/commit/39100eca4915e4fe86a6912aa97dde86ed72e015\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eRuff linter and formatter.\u003c/strong\u003e Added Ruff as the Python linter and formatter, replacing the black-based workflow for better code quality with near-instant execution. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22576\"\u003e#22576\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/22462\"\u003e#22462\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eOffline code formatting support.\u003c/strong\u003e The black formatter for Python code editing is now bundled locally in the Docker image, enabling code formatting to work in air-gapped deployments where client browsers cannot reach PyPI. Formatting failures no longer block saves, allowing code to be preserved even when offline. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22509\"\u003e#22509\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8507e5eb0d18896f1bbf990a00a4361aec171a30\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eMarkdown file editing.\u003c/strong\u003e Users can now edit and save Markdown files directly in the file navigator, with empty files automatically switching to editor mode for immediate editing. \u003ca href=\"https://github.com/open-webui/open-webui/commit/47e47e42af682e7f75c8359999f7cdf969bf903e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🍔 \u003cstrong\u003eModel bulk actions menu.\u003c/strong\u003e Users can now quickly enable, disable, show, or hide multiple models at once using a new hamburger menu on the workspace Models page filter bar, with actions respecting the current search and filter settings. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22484\"\u003e#22484\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eFiles list pagination.\u003c/strong\u003e The files list API now supports pagination, returning paginated results with a total count for easier navigation through large file collections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f9756de693a93e918c037d757afddb7defc847e4\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖇 \u003cstrong\u003eWeb fetch content length config.\u003c/strong\u003e Administrators can now configure the maximum characters to return from fetched URLs via WEB_FETCH_MAX_CONTENT_LENGTH environment variable or the admin settings page, instead of the previous hardcoded 50K limit. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b171b0216b916745420c7caf513093a315ed9560\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22774\"\u003e#22774\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eOllama Anthropic endpoint support.\u003c/strong\u003e The Ollama proxy now supports the Anthropic-compatible /v1/messages endpoint, allowing clients using the Anthropic API format to work through Open WebUI with proper authentication and model access controls. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f23296b22d3304e5bfcd19151e5802eec55bd98f\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22861\"\u003e#22861\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eWriting block rendering.\u003c/strong\u003e Responses from OpenAI models that include :::writing blocks are now rendered as formatted content in a styled container with a copy button, instead of displaying raw marker text. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22672\"\u003e#22672\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/53b8a1f71bd0cb0a0122175ad5210da492018728\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eMemory deletion confirmation.\u003c/strong\u003e Users are now asked to confirm before deleting individual memory entries, with the memory content displayed for review. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22888\"\u003e#22888\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📓 \u003cstrong\u003eMulti-artifact HTML rendering.\u003c/strong\u003e Code blocks with multiple HTML sections now render as separate artifacts instead of merging into one, allowing models to display distinct interactive components. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a6bf78e14a13864e72db87426da4f5996abe716\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚩 \u003cstrong\u003eDrag chats as references.\u003c/strong\u003e Users can now drag chats from the sidebar and drop them into the message input to add them as Reference Chats. \u003ca href=\"https://github.com/open-webui/open-webui/commit/ebb7ce2092efc8d78da4974623647dbd18b6e372\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eTerminal system prompts.\u003c/strong\u003e Terminal servers can now provide custom system prompts that are automatically included when their tools are used. \u003ca href=\"https://github.com/open-webui/open-webui/commit/6a9d67b5bb4c93fd343b334bee3e37703dff59f6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eTerminal state persistence.\u003c/strong\u003e The selected terminal server and its enabled state now persist across page loads, making terminal usage more seamless. \u003ca href=\"https://github.com/open-webui/open-webui/commit/d577ff1e4af750dda09e558dac7edb8dd2470850\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eTerminal folder downloads.\u003c/strong\u003e Users can now download folders as ZIP archives and bulk-download multiple selected files as a single ZIP directly from the File Navigator toolbar, making file exports faster and more convenient. \u003ca href=\"https://github.com/open-webui/open-webui/commit/3841e85abb3ea3e8d8b364dff0102f0124844d22\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/cf60b1882f1929200649b59f867289dea54e4210\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eMCP OAuth 2.1 static credentials.\u003c/strong\u003e MCP servers that require static client_id and client_secret can now be connected using a new OAuth 2.1 Static auth type, enabling integration with MCP servers that don't support dynamic client registration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/22266\"\u003e#22266\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/601bb783587a3e965cf88c148e4856b988655b13\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎪 \u003cstrong\u003eCollapsible tool and thinking groups.\u003c/strong\u003e Consecutive tool calls and reasoning blocks are now grouped into a single collapsible summary (e.g., \u0026quot;Explored tool1, tool2\u0026quot;), keeping chat responses clean and readable while preserving full detail on expand. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21604\"\u003e#21604\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/261aec8c864646eb7215be0d5c14a79cad3cb93f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eGeneral improvements.\u003c/strong\u003e Various improvements were implemented across the application to enhance performance, stability, and security.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4d058a125b17eb57212af5eab98d683548d546e3\"\u003e\u003ccode\u003e4d058a1\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/23035\"\u003e#23035\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f12252531066762c85d8e180143bfc74260eacc9\"\u003e\u003ccode\u003ef122525\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f5f128620a404396bd56895d0e039f3c79f905be\"\u003e\u003ccode\u003ef5f1286\u003c/code\u003e\u003c/a\u003e chore: ci\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/06635898d0960235d0bb1931f595c772e2e3652b\"\u003e\u003ccode\u003e0663589\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0ded0b706919896e79bb43f3733f84d22889302d\"\u003e\u003ccode\u003e0ded0b7\u003c/code\u003e\u003c/a\u003e chore: ci\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0fa246a1c3ad3aa85945fac487494b5bd69603ad\"\u003e\u003ccode\u003e0fa246a\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8cb47aebae5e924fcd936741649d97cf0680032f\"\u003e\u003ccode\u003e8cb47ae\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/bfc606a9e3065065bd9bfe4e1e9206236a94e987\"\u003e\u003ccode\u003ebfc606a\u003c/code\u003e\u003c/a\u003e fix: align file context injection by user-role messages for native FC (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22776\"\u003e#22776\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7a21933d100733963fb54ebdd208825d1f5b8411\"\u003e\u003ccode\u003e7a21933\u003c/code\u003e\u003c/a\u003e chore: changelog (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/22569\"\u003e#22569\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9364e2fb74a0a69b2618a761526165b63d4815ff\"\u003e\u003ccode\u003e9364e2f\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.8.8...v0.8.11\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.8.8-slim\u0026new-version=v0.8.11-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/36","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/36","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/36/packages"}},{"old_version":"0.6.43","new_version":"0.8.5","update_type":"minor","path":"/charts/open-webui","pr_created_at":"2026-02-24T07:28:24.000Z","version_change":"0.6.43 → 0.8.5","issue":{"uuid":"3982029016","node_id":"PR_kwDOPvrhr87F2Epp","number":46,"state":"closed","title":"Bump open-webui/open-webui from 0.6.43 to 0.8.5 in /charts/open-webui","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-03-01T07:09:02.000Z","author_association":null,"state_reason":null,"created_at":"2026-02-24T07:28:24.000Z","updated_at":"2026-03-01T07:09:03.000Z","time_to_close":430838,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.43","new_version":"0.8.5","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/charts/open-webui","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.43 to 0.8.5.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.5\u003c/h2\u003e\n\u003ch2\u003e[0.8.5] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eVoice dictation shortcut.\u003c/strong\u003e Users can now toggle voice dictation using Cmd+Shift+L (or Ctrl+Shift+L on Windows/Linux), making it faster to start and stop dictation without clicking the microphone button.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eModel access KeyError fix.\u003c/strong\u003e The /api/models endpoint no longer crashes with a 500 error when models have incomplete info metadata missing the user_id field (e.g. models using global default metadata).\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eFrontend initialization resilience.\u003c/strong\u003e The app layout now gracefully handles individual API failures during initialization (getModels, getBanners, getTools, getUserSettings, setToolServers) instead of blocking the entire page load when any single call fails.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eBackend config null safety.\u003c/strong\u003e Language detection during app initialization no longer crashes when the backend config fetch fails, preventing a secondary cause of infinite loading.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.4\u003c/h2\u003e\n\u003ch2\u003e[0.8.4] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛜 \u003cstrong\u003eProvider URL suggestions.\u003c/strong\u003e The connection form now displays a dropdown with suggested URLs for popular AI providers, making it easier to configure connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/49c36238d01aaff5466344ecd316a6dd3edd74a3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ \u003cstrong\u003eAnthropic model fetching.\u003c/strong\u003e The system now properly fetches available models from the Anthropic API, ensuring all Anthropic models are accessible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e9d852545cc17f0eeb8bdcfa77575a80fed8706d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eNo models prompt.\u003c/strong\u003e When no models are available, a helpful prompt now guides users to manage their provider connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/a0195cd5ae9b9915295839cd0a5fbac5a1b0bfa2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConnection enable/disable toggles.\u003c/strong\u003e Individual provider connections can now be enabled or disabled from both admin and user settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/990c638f6cf91507b61898f454c26f9516114c36\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⏸️ \u003cstrong\u003ePrompt enable/disable toggle.\u003c/strong\u003e Users can now enable or disable prompts directly from the prompts list using a toggle switch, without needing to delete and recreate them. Inactive prompts display an \u0026quot;Inactive\u0026quot; badge and are still visible in the list. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eMemory deletion.\u003c/strong\u003e Agents can now delete specific memories that are no longer relevant, duplicated, or incorrect, giving better control over stored memory content. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eMemory listing.\u003c/strong\u003e Agents can now list all stored memories, enabling them to identify which memories to manage or delete based on the complete memory inventory. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eAuto pip install toggle.\u003c/strong\u003e Administrators can now disable automatic pip package installation from function frontmatter requirements using the ENABLE_PIP_INSTALL_FRONTMATTER_REQUIREMENTS environment variable, providing more control over function dependency management. \u003ca href=\"https://github.com/open-webui/open-webui/commit/8bfab327ec5f635f9fe93c26efd198712ff7116d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eAnthropic Messages API proxy.\u003c/strong\u003e A new API endpoint now supports the Anthropic Messages API format, allowing tools like Claude Code to authenticate through Open WebUI and access configured models. Tool calls are now properly supported in streaming responses with correct multi-block indexing, and error status from tools is propagated correctly. The endpoint converts requests to OpenAI format internally, routes them through the existing chat pipeline, and returns responses in Anthropic format. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21390\"\u003e#21390\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/91a0301c9e22e93295a7c471d83592a802560795\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a9312d25373d3aa161788598f87180b8db11c5b6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eMulti-device OAuth sessions.\u003c/strong\u003e Users can now stay logged in on multiple devices simultaneously with OAuth, as re-logging in no longer terminates existing sessions. The oldest sessions are automatically pruned when the session limit is exceeded. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21647\"\u003e#21647\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/ae05586fdabf318d551b53ede41575355d3b9e2b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth group default share setting.\u003c/strong\u003e Administrators can now configure the default sharing setting for OAuth-created groups using the OAUTH_GROUP_DEFAULT_SHARE environment variable, allowing control over whether new groups default to private or shared with members. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21679\"\u003e#21679\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4b9f821b58007d4efa4aa16a4995b23126e08a88\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eKnowledge base import behavior.\u003c/strong\u003e The web content import endpoint now supports a configurable overwrite flag, allowing users to add multiple URLs to the same knowledge base instead of replacing existing content. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21613\"\u003e#21613\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21336\"\u003e#21336\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4bef69cc6344ff809090441aa6bced573a2aa838\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSkill JSON import support.\u003c/strong\u003e Skills can now be imported from both JSON and Markdown files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21511\"\u003e#21511\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eYou.com web search provider.\u003c/strong\u003e A new web search provider option for You.com is now available, giving users another search engine choice for web-enabled models. The You.com provider enriches search results by including both descriptions and snippets for better context. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21599\"\u003e#21599\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eMessage list performance.\u003c/strong\u003e Loading conversation history when sending messages is now significantly faster, improving response latency before the model starts generating. This also speeds up chat search and RAG context building. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21588\"\u003e#21588\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eConcurrent embedding request control.\u003c/strong\u003e Administrators can now control the maximum number of concurrent embedding API requests using the RAG_EMBEDDING_CONCURRENT_REQUESTS environment variable, helping manage API rate limits while maintaining embedding performance. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21662\"\u003e#21662\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/5d4547f934b6fbe751bb2041f9597fe11ddf8e43\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage upsert optimization.\u003c/strong\u003e Loading chat data during message saving is now significantly faster by eliminating a redundant database call that occurred on every message upsert, which happens many times during streaming responses. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21592\"\u003e#21592\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage send optimization.\u003c/strong\u003e Loading chat data during message sending is now significantly faster by eliminating unnecessary full conversation history loads. The system now uses targeted queries that fetch only the needed data instead of loading entire chat objects with all message history. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21596\"\u003e#21596\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eTag filtering optimization.\u003c/strong\u003e Chat search with tag filtering now uses more efficient database queries, making filtered searches significantly faster. \u003ca href=\"https://github.com/open-webui/open-webui/commit/139f02a9d9fa2ffffcc96aa0de8af8ef51b6bcf2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eShared chat loading optimization.\u003c/strong\u003e The shared chats endpoint now loads only the needed columns instead of the full conversation history, making shared chat listings significantly faster. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21614\"\u003e#21614\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eArchived and pinned chat loading.\u003c/strong\u003e Loading archived and pinned chat lists is now significantly faster by loading only the needed columns instead of full conversation data. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21591\"\u003e#21591\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eChat title query optimization.\u003c/strong\u003e Retrieving chat titles now queries only the title column instead of the entire conversation history, making title lookups significantly faster and reducing database load. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21590\"\u003e#21590\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eBatch access grants for multiple resources.\u003c/strong\u003e Loading channels, knowledge bases, models, notes, prompts, skills, and tools now uses batch database queries for access grants instead of individual queries per item, significantly reducing database load. For 30 items, this reduces approximately 31 queries to just 3. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21616\"\u003e#21616\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eNotes list payload optimization.\u003c/strong\u003e Notes list and search endpoints now return only a 200-character preview instead of the full note content, reducing response payload from ~167 MB to ~10 KB for 60 notes and eliminating N+1 queries for access grants. The Notes tab now loads in seconds instead of tens of seconds. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21549\"\u003e#21549\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eTools list performance.\u003c/strong\u003e Loading the tools list is now significantly faster by deferring content and specs fields from database queries, and using cached tool modules instead of reloading them for each request. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b48594a16680cc77921a4ed1a11ffa07df7edc60\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eGroup description display.\u003c/strong\u003e The admin groups list now shows each group's description, making it easier for administrators to identify groups at a glance.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eSort by dropdown.\u003c/strong\u003e Administrators can now sort groups using a dropdown menu with options for Name or Members, replacing the previous clickable column headers.\u003c/li\u003e\n\u003cli\u003e📶 \u003cstrong\u003eAdmin groups list sorting.\u003c/strong\u003e The Group and Users columns in the admin groups list are now clickable for sorting, allowing administrators to sort groups alphabetically by name or numerically by member count. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21692\"\u003e#21692\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔽 \u003cstrong\u003eRich UI auto-scroll.\u003c/strong\u003e The view now automatically scrolls to action-generated Rich UI content once it renders, ensuring users can see the results without manually scrolling. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21698\"\u003e#21698\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21482\"\u003e#21482\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAdmin analytics toggle.\u003c/strong\u003e Administrators can now enable or disable the analytics feature using the ENABLE_ADMIN_ANALYTICS environment variable, giving more control over available admin features. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21651\"\u003e#21651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/35598b8017557258b8c9ee3469d320adb0140751\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAnalytics sorting enhancement.\u003c/strong\u003e The Analytics dashboard now supports sorting by Tokens column for both Model Usage and User Usage tables, and the Share/Percentage columns are now clickable for sorting. Administrators can more easily identify the most token-consuming models and users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/053a33631f575ae1ad3123190a9e820b4057f62d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📑 \u003cstrong\u003eFetch URL citation sources.\u003c/strong\u003e When models fetch URLs during tool calling, the fetched URLs now appear as clickable citation sources in the UI with content previews, matching the existing behavior of web search and knowledge file tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21669\"\u003e#21669\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.8.5] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eVoice dictation shortcut.\u003c/strong\u003e Users can now toggle voice dictation using Cmd+Shift+L (or Ctrl+Shift+L on Windows/Linux), making it faster to start and stop dictation without clicking the microphone button.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eModel access KeyError fix.\u003c/strong\u003e The /api/models endpoint no longer crashes with a 500 error when models have incomplete info metadata missing the user_id field (e.g. models using global default metadata).\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eFrontend initialization resilience.\u003c/strong\u003e The app layout now gracefully handles individual API failures during initialization (getModels, getBanners, getTools, getUserSettings, setToolServers) instead of blocking the entire page load when any single call fails.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eBackend config null safety.\u003c/strong\u003e Language detection during app initialization no longer crashes when the backend config fetch fails, preventing a secondary cause of infinite loading.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.8.4] - 2026-02-23\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛜 \u003cstrong\u003eProvider URL suggestions.\u003c/strong\u003e The connection form now displays a dropdown with suggested URLs for popular AI providers, making it easier to configure connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/49c36238d01aaff5466344ecd316a6dd3edd74a3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ \u003cstrong\u003eAnthropic model fetching.\u003c/strong\u003e The system now properly fetches available models from the Anthropic API, ensuring all Anthropic models are accessible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e9d852545cc17f0eeb8bdcfa77575a80fed8706d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eNo models prompt.\u003c/strong\u003e When no models are available, a helpful prompt now guides users to manage their provider connections. \u003ca href=\"https://github.com/open-webui/open-webui/commit/a0195cd5ae9b9915295839cd0a5fbac5a1b0bfa2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConnection enable/disable toggles.\u003c/strong\u003e Individual provider connections can now be enabled or disabled from both admin and user settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/990c638f6cf91507b61898f454c26f9516114c36\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⏸️ \u003cstrong\u003ePrompt enable/disable toggle.\u003c/strong\u003e Users can now enable or disable prompts directly from the prompts list using a toggle switch, without needing to delete and recreate them. Inactive prompts display an \u0026quot;Inactive\u0026quot; badge and are still visible in the list. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eMemory deletion.\u003c/strong\u003e Agents can now delete specific memories that are no longer relevant, duplicated, or incorrect, giving better control over stored memory content. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eMemory listing.\u003c/strong\u003e Agents can now list all stored memories, enabling them to identify which memories to manage or delete based on the complete memory inventory. \u003ca href=\"https://github.com/open-webui/open-webui/commit/094ed0b48cb86b9b6aff3c93f522072d11230761\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eAuto pip install toggle.\u003c/strong\u003e Administrators can now disable automatic pip package installation from function frontmatter requirements using the ENABLE_PIP_INSTALL_FRONTMATTER_REQUIREMENTS environment variable, providing more control over function dependency management. \u003ca href=\"https://github.com/open-webui/open-webui/commit/8bfab327ec5f635f9fe93c26efd198712ff7116d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eAnthropic Messages API proxy.\u003c/strong\u003e A new API endpoint now supports the Anthropic Messages API format, allowing tools like Claude Code to authenticate through Open WebUI and access configured models. Tool calls are now properly supported in streaming responses with correct multi-block indexing, and error status from tools is propagated correctly. The endpoint converts requests to OpenAI format internally, routes them through the existing chat pipeline, and returns responses in Anthropic format. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21390\"\u003e#21390\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/91a0301c9e22e93295a7c471d83592a802560795\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a9312d25373d3aa161788598f87180b8db11c5b6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eMulti-device OAuth sessions.\u003c/strong\u003e Users can now stay logged in on multiple devices simultaneously with OAuth, as re-logging in no longer terminates existing sessions. The oldest sessions are automatically pruned when the session limit is exceeded. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21647\"\u003e#21647\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/ae05586fdabf318d551b53ede41575355d3b9e2b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth group default share setting.\u003c/strong\u003e Administrators can now configure the default sharing setting for OAuth-created groups using the OAUTH_GROUP_DEFAULT_SHARE environment variable, allowing control over whether new groups default to private or shared with members. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21679\"\u003e#21679\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4b9f821b58007d4efa4aa16a4995b23126e08a88\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eKnowledge base import behavior.\u003c/strong\u003e The web content import endpoint now supports a configurable overwrite flag, allowing users to add multiple URLs to the same knowledge base instead of replacing existing content. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21613\"\u003e#21613\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21336\"\u003e#21336\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4bef69cc6344ff809090441aa6bced573a2aa838\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSkill JSON import support.\u003c/strong\u003e Skills can now be imported from both JSON and Markdown files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21511\"\u003e#21511\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eYou.com web search provider.\u003c/strong\u003e A new web search provider option for You.com is now available, giving users another search engine choice for web-enabled models. The You.com provider enriches search results by including both descriptions and snippets for better context. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21599\"\u003e#21599\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eMessage list performance.\u003c/strong\u003e Loading conversation history when sending messages is now significantly faster, improving response latency before the model starts generating. This also speeds up chat search and RAG context building. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21588\"\u003e#21588\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eConcurrent embedding request control.\u003c/strong\u003e Administrators can now control the maximum number of concurrent embedding API requests using the RAG_EMBEDDING_CONCURRENT_REQUESTS environment variable, helping manage API rate limits while maintaining embedding performance. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21662\"\u003e#21662\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/5d4547f934b6fbe751bb2041f9597fe11ddf8e43\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage upsert optimization.\u003c/strong\u003e Loading chat data during message saving is now significantly faster by eliminating a redundant database call that occurred on every message upsert, which happens many times during streaming responses. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21592\"\u003e#21592\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eMessage send optimization.\u003c/strong\u003e Loading chat data during message sending is now significantly faster by eliminating unnecessary full conversation history loads. The system now uses targeted queries that fetch only the needed data instead of loading entire chat objects with all message history. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21596\"\u003e#21596\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eTag filtering optimization.\u003c/strong\u003e Chat search with tag filtering now uses more efficient database queries, making filtered searches significantly faster. \u003ca href=\"https://github.com/open-webui/open-webui/commit/139f02a9d9fa2ffffcc96aa0de8af8ef51b6bcf2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eShared chat loading optimization.\u003c/strong\u003e The shared chats endpoint now loads only the needed columns instead of the full conversation history, making shared chat listings significantly faster. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21614\"\u003e#21614\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eArchived and pinned chat loading.\u003c/strong\u003e Loading archived and pinned chat lists is now significantly faster by loading only the needed columns instead of full conversation data. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21591\"\u003e#21591\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eChat title query optimization.\u003c/strong\u003e Retrieving chat titles now queries only the title column instead of the entire conversation history, making title lookups significantly faster and reducing database load. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21590\"\u003e#21590\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eBatch access grants for multiple resources.\u003c/strong\u003e Loading channels, knowledge bases, models, notes, prompts, skills, and tools now uses batch database queries for access grants instead of individual queries per item, significantly reducing database load. For 30 items, this reduces approximately 31 queries to just 3. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21616\"\u003e#21616\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eNotes list payload optimization.\u003c/strong\u003e Notes list and search endpoints now return only a 200-character preview instead of the full note content, reducing response payload from ~167 MB to ~10 KB for 60 notes and eliminating N+1 queries for access grants. The Notes tab now loads in seconds instead of tens of seconds. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21549\"\u003e#21549\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eTools list performance.\u003c/strong\u003e Loading the tools list is now significantly faster by deferring content and specs fields from database queries, and using cached tool modules instead of reloading them for each request. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b48594a16680cc77921a4ed1a11ffa07df7edc60\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eGroup description display.\u003c/strong\u003e The admin groups list now shows each group's description, making it easier for administrators to identify groups at a glance.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eSort by dropdown.\u003c/strong\u003e Administrators can now sort groups using a dropdown menu with options for Name or Members, replacing the previous clickable column headers.\u003c/li\u003e\n\u003cli\u003e📶 \u003cstrong\u003eAdmin groups list sorting.\u003c/strong\u003e The Group and Users columns in the admin groups list are now clickable for sorting, allowing administrators to sort groups alphabetically by name or numerically by member count. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21692\"\u003e#21692\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔽 \u003cstrong\u003eRich UI auto-scroll.\u003c/strong\u003e The view now automatically scrolls to action-generated Rich UI content once it renders, ensuring users can see the results without manually scrolling. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21698\"\u003e#21698\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21482\"\u003e#21482\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAdmin analytics toggle.\u003c/strong\u003e Administrators can now enable or disable the analytics feature using the ENABLE_ADMIN_ANALYTICS environment variable, giving more control over available admin features. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21651\"\u003e#21651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/35598b8017557258b8c9ee3469d320adb0140751\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eAnalytics sorting enhancement.\u003c/strong\u003e The Analytics dashboard now supports sorting by Tokens column for both Model Usage and User Usage tables, and the Share/Percentage columns are now clickable for sorting. Administrators can more easily identify the most token-consuming models and users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/053a33631f575ae1ad3123190a9e820b4057f62d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📑 \u003cstrong\u003eFetch URL citation sources.\u003c/strong\u003e When models fetch URLs during tool calling, the fetched URLs now appear as clickable citation sources in the UI with content previews, matching the existing behavior of web search and knowledge file tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21669\"\u003e#21669\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eAdmin settings tab navigation.\u003c/strong\u003e The admin settings sidebar now supports native browser tab opening, allowing users to middle-click or right-click to open settings pages in new tabs. The navigation was converted from button-based to anchor-based elements. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21721\"\u003e#21721\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eModel visibility badges.\u003c/strong\u003e The Admin Settings Models page now displays Public or Private badges directly on each model, making it easy to identify model access levels at a glance without opening the edit screen. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21732\"\u003e#21732\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/29217cb430bd47827ebb20782b264ae7b0f233bb\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1ac3dd4a893e13803e7b889611303c4a7a5cc470\"\u003e\u003ccode\u003e1ac3dd4\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21773\"\u003e#21773\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/55c489146cf64d80630829a0ac98aa10c073925e\"\u003e\u003ccode\u003e55c4891\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ffcf97e3e1908c5c0879f5663f670981828d471c\"\u003e\u003ccode\u003effcf97e\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/95bde946ba4db0e6f88970e8507d5c404c53d6b1\"\u003e\u003ccode\u003e95bde94\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/895c805e626e59efe48518aca563b4870ba213af\"\u003e\u003ccode\u003e895c805\u003c/code\u003e\u003c/a\u003e feat: dictation toggle\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2ed3055c42ae18e3372081c18629963b0e244a62\"\u003e\u003ccode\u003e2ed3055\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21618\"\u003e#21618\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1792f668f2cff0beb7100a701965a73b3954c086\"\u003e\u003ccode\u003e1792f66\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1d3d3b2d94f016a4357470dcb89253379c43524c\"\u003e\u003ccode\u003e1d3d3b2\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9044abf3bb78eb6ce139102191b79b98cee654f1\"\u003e\u003ccode\u003e9044abf\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/424dba443c578008a1dfa0dd999069a12ab74a3a\"\u003e\u003ccode\u003e424dba4\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.43...v0.8.5\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.43\u0026new-version=0.8.5)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/darkhonor/helm-charts/pull/46","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/darkhonor%2Fhelm-charts/issues/46","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/46/packages"}},{"old_version":"0.6.43","new_version":"0.8.3","update_type":"minor","path":"/charts/open-webui","pr_created_at":"2026-02-20T07:28:22.000Z","version_change":"0.6.43 → 0.8.3","issue":{"uuid":"3967055636","node_id":"PR_kwDOPvrhr87FFpf3","number":42,"state":"closed","title":"Bump open-webui/open-webui from 0.6.43 to 0.8.3 in /charts/open-webui","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-02-24T07:28:26.000Z","author_association":null,"state_reason":null,"created_at":"2026-02-20T07:28:22.000Z","updated_at":"2026-02-24T07:28:28.000Z","time_to_close":345604,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.43","new_version":"0.8.3","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/charts/open-webui","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.43 to 0.8.3.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.3\u003c/h2\u003e\n\u003ch2\u003e[0.8.3] - 2026-02-17\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eModel edit shortcut.\u003c/strong\u003e Users can now edit models directly from the model selector dropdown menu, making it faster to modify model settings without navigating to separate admin or workspace pages. \u003ca href=\"https://github.com/open-webui/open-webui/commit/519ff40cb69cdc1d215cee369e9db70ff7438153\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eImage edit API background support.\u003c/strong\u003e The image edit API now supports the background parameter for OpenAI's gpt-image-1 model, enabling background transparency control (\u0026quot;transparent\u0026quot;, \u0026quot;opaque\u0026quot;, \u0026quot;auto\u0026quot;) when the feature is exposed in the UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21459\"\u003e#21459\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFaster model filtering.\u003c/strong\u003e Model access control filtering no longer makes a redundant database query to re-fetch model info that is already available in memory, reducing latency when loading model lists for non-admin users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/34cd3d79e8688f589e3dd2f03415f8a8f9a13115\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call display improvements.\u003c/strong\u003e Tool call results now display arguments in a cleaner key-value format instead of raw JSON, with a responsive layout that shows only the tool name on narrow screens and the full label on wider screens, preventing text wrapping to multiple lines. \u003ca href=\"https://github.com/open-webui/open-webui/commit/2ce935bdb10d2b26b230cd54cb649f5c667ed96a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eGeneral improvements.\u003c/strong\u003e Various improvements were implemented across the application to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📧 \u003cstrong\u003eUSER_EMAIL variable fix.\u003c/strong\u003e The {{USER_EMAIL}} template variable now correctly returns the user's email address instead of \u0026quot;Unknown\u0026quot; in prompts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21479\"\u003e#21479\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21465\"\u003e#21465\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage and file attachment handling fixes.\u003c/strong\u003e Uploaded images are now correctly sent to vision-enabled models, and file attachments now work even when no user text is entered alongside a system prompt. This fixes two issues where the backend was not properly processing file attachments: images weren't converted to the expected format for API requests, and file context was dropped when the user sent only a file without accompanying text. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1053d94c7ef7b8b78682dd73586b65a84d202a1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21477\"\u003e#21477\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21457\"\u003e#21457\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eMissing function error handling.\u003c/strong\u003e Models that reference deleted functions no longer cause the entire /api/models endpoint to crash; instead, the missing functions are skipped and logged, allowing the rest of the models to load successfully. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21476\"\u003e#21476\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21464\"\u003e#21464\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eStartup model pre-fetch error handling.\u003c/strong\u003e If model pre-fetching fails during app startup, the application now logs a warning and continues instead of crashing entirely. \u003ca href=\"https://github.com/open-webui/open-webui/commit/337109e99ce390f55a9085d0a301853637923779\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eFunction module loading error handling.\u003c/strong\u003e Function modules that fail to load during startup or model processing are now caught and logged, preventing crashes when models reference functions with loading errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/15b893e651de71b033408e1b713e0b51f6829ab8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003ePostgreSQL group query fix.\u003c/strong\u003e The '/api/v1/groups/' endpoint no longer fails with a GROUP BY error when using PostgreSQL; member counts are now calculated using correlated subqueries for better database compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21458\"\u003e#21458\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21467\"\u003e#21467\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.2\u003c/h2\u003e\n\u003ch2\u003e[0.8.2] - 2026-02-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eSkill content handling.\u003c/strong\u003e User-selected skills now have their full content injected into the chat, while model-attached skills only display name and description in the available skills list. This allows users to override skill behavior while model-attached skills remain flexible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/393c0071dc612c5ac982fb37dfc0288cb9911439\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eChat toggles now control built-in tools.\u003c/strong\u003e Users can now disable web search, image generation, and code execution on a per-conversation basis, even when those tools are enabled as builtin tools on the model. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20641\"\u003e#20641\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21318\"\u003e#21318\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c46ef3b63bcc1e2e9adbdd18fab82c4bbe33ff6c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1a1e64d2e9ad953b2bc2a9543e9a308b7c669c8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage preview in file modal.\u003c/strong\u003e Images uploaded to chats can now be previewed directly in the file management modal, making it easier to identify and manage image files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21413\"\u003e#21413\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e1b3e7252c1896c04d498547908f0fce111434e1\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eBatch tag operations.\u003c/strong\u003e Tag creation, deletion, and orphan cleanup for chats now use batch database queries instead of per-tag loops, significantly reducing database round trips when updating, archiving, or deleting chats with multiple tags. \u003ca href=\"https://github.com/open-webui/open-webui/commit/c748c3ede\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eFaster group list loading.\u003c/strong\u003e Group lists and search results now load with a single database query that joins member counts, replacing the previous pattern of fetching groups first and then counting members in a separate batch query. \u003ca href=\"https://github.com/open-webui/open-webui/commit/33308022f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eSkills sharing permissions.\u003c/strong\u003e Administrators can now control skills sharing and public sharing permissions per-group, matching the existing capabilities for tools, knowledge, and prompts. \u003ca href=\"https://github.com/open-webui/open-webui/commit/88401e91c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eLong content truncation in preview modals.\u003c/strong\u003e Citation and file content modals now truncate markdown-rendered content at 10,000 characters with a \u0026quot;Show all\u0026quot; expansion button, preventing UI jank when previewing very large documents.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eTranslation updates.\u003c/strong\u003e Translations for Spanish and German were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth session error handling.\u003c/strong\u003e Corrupted OAuth sessions are now gracefully handled and automatically cleaned up instead of causing errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7e224e4a536b07ec008613f06592e34050e7067c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eTask model selector validation.\u003c/strong\u003e The task model selector in admin settings now correctly accepts models based on the new access grants system instead of rejecting all models with an incorrect error. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a2595f0706d0c9d809ae7746001cf799f98db1d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eTool call message preservation.\u003c/strong\u003e Models no longer hallucinate tool outputs in multi-turn conversations because tool call history is now properly preserved instead of being merged into assistant messages. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21098\"\u003e#21098\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20600\"\u003e#20600\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f2aca781c87244cffc130aa2722e700c19a81d66\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool server startup initialization.\u003c/strong\u003e External tool servers configured via the \u0026quot;TOOL_SERVER_CONNECTIONS\u0026quot; environment variable now initialize automatically on startup, eliminating the need to manually visit the Admin Panel and save for tools to become available. This enables proper GitOps and containerized deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18140\"\u003e#18140\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/20914\"\u003e#20914\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f20cc6d7e6da493eb75ca1618f5cbd068fa57684\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e♻️ \u003cstrong\u003eResource handle cleanup.\u003c/strong\u003e File handles are now properly closed during audio transcription and pipeline uploads, preventing resource leaks that could cause system instability over time. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21411\"\u003e#21411\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eStrikethrough shortcut conflict fix.\u003c/strong\u003e Pressing Ctrl+Shift+S to toggle the sidebar no longer causes text to become struck through in the chat input, by disabling the TipTap Strike extension's default keyboard shortcut when rich text mode is off. \u003ca href=\"https://github.com/open-webui/open-webui/commit/38ae91ae2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call finish_reason fix.\u003c/strong\u003e API responses now correctly set finish_reason to \u0026quot;tool_calls\u0026quot; instead of \u0026quot;stop\u0026quot; when tool calls are present, fixing an issue where external API clients (such as OpenCode) would halt prematurely after tool execution when routing Ollama models through the Open WebUI API. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20896\"\u003e#20896\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.1\u003c/h2\u003e\n\u003ch2\u003e[0.8.1] - 2026-02-14\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!CAUTION]\n⚠️ \u003cstrong\u003eDatabase Migrations\u003c/strong\u003e: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.8.3] - 2026-02-17\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e✏️ \u003cstrong\u003eModel edit shortcut.\u003c/strong\u003e Users can now edit models directly from the model selector dropdown menu, making it faster to modify model settings without navigating to separate admin or workspace pages. \u003ca href=\"https://github.com/open-webui/open-webui/commit/519ff40cb69cdc1d215cee369e9db70ff7438153\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eImage edit API background support.\u003c/strong\u003e The image edit API now supports the background parameter for OpenAI's gpt-image-1 model, enabling background transparency control (\u0026quot;transparent\u0026quot;, \u0026quot;opaque\u0026quot;, \u0026quot;auto\u0026quot;) when the feature is exposed in the UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21459\"\u003e#21459\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFaster model filtering.\u003c/strong\u003e Model access control filtering no longer makes a redundant database query to re-fetch model info that is already available in memory, reducing latency when loading model lists for non-admin users. \u003ca href=\"https://github.com/open-webui/open-webui/commit/34cd3d79e8688f589e3dd2f03415f8a8f9a13115\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call display improvements.\u003c/strong\u003e Tool call results now display arguments in a cleaner key-value format instead of raw JSON, with a responsive layout that shows only the tool name on narrow screens and the full label on wider screens, preventing text wrapping to multiple lines. \u003ca href=\"https://github.com/open-webui/open-webui/commit/2ce935bdb10d2b26b230cd54cb649f5c667ed96a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eGeneral improvements.\u003c/strong\u003e Various improvements were implemented across the application to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, and Traditional Chinese were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📧 \u003cstrong\u003eUSER_EMAIL variable fix.\u003c/strong\u003e The {{USER_EMAIL}} template variable now correctly returns the user's email address instead of \u0026quot;Unknown\u0026quot; in prompts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21479\"\u003e#21479\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21465\"\u003e#21465\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage and file attachment handling fixes.\u003c/strong\u003e Uploaded images are now correctly sent to vision-enabled models, and file attachments now work even when no user text is entered alongside a system prompt. This fixes two issues where the backend was not properly processing file attachments: images weren't converted to the expected format for API requests, and file context was dropped when the user sent only a file without accompanying text. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1053d94c7ef7b8b78682dd73586b65a84d202a1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21477\"\u003e#21477\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21457\"\u003e#21457\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eMissing function error handling.\u003c/strong\u003e Models that reference deleted functions no longer cause the entire /api/models endpoint to crash; instead, the missing functions are skipped and logged, allowing the rest of the models to load successfully. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21476\"\u003e#21476\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21464\"\u003e#21464\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eStartup model pre-fetch error handling.\u003c/strong\u003e If model pre-fetching fails during app startup, the application now logs a warning and continues instead of crashing entirely. \u003ca href=\"https://github.com/open-webui/open-webui/commit/337109e99ce390f55a9085d0a301853637923779\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eFunction module loading error handling.\u003c/strong\u003e Function modules that fail to load during startup or model processing are now caught and logged, preventing crashes when models reference functions with loading errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/15b893e651de71b033408e1b713e0b51f6829ab8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003ePostgreSQL group query fix.\u003c/strong\u003e The '/api/v1/groups/' endpoint no longer fails with a GROUP BY error when using PostgreSQL; member counts are now calculated using correlated subqueries for better database compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21458\"\u003e#21458\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21467\"\u003e#21467\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.8.2] - 2026-02-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eSkill content handling.\u003c/strong\u003e User-selected skills now have their full content injected into the chat, while model-attached skills only display name and description in the available skills list. This allows users to override skill behavior while model-attached skills remain flexible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/393c0071dc612c5ac982fb37dfc0288cb9911439\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eChat toggles now control built-in tools.\u003c/strong\u003e Users can now disable web search, image generation, and code execution on a per-conversation basis, even when those tools are enabled as builtin tools on the model. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20641\"\u003e#20641\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21318\"\u003e#21318\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c46ef3b63bcc1e2e9adbdd18fab82c4bbe33ff6c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1a1e64d2e9ad953b2bc2a9543e9a308b7c669c8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage preview in file modal.\u003c/strong\u003e Images uploaded to chats can now be previewed directly in the file management modal, making it easier to identify and manage image files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21413\"\u003e#21413\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e1b3e7252c1896c04d498547908f0fce111434e1\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eBatch tag operations.\u003c/strong\u003e Tag creation, deletion, and orphan cleanup for chats now use batch database queries instead of per-tag loops, significantly reducing database round trips when updating, archiving, or deleting chats with multiple tags. \u003ca href=\"https://github.com/open-webui/open-webui/commit/c748c3ede\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eFaster group list loading.\u003c/strong\u003e Group lists and search results now load with a single database query that joins member counts, replacing the previous pattern of fetching groups first and then counting members in a separate batch query. \u003ca href=\"https://github.com/open-webui/open-webui/commit/33308022f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eSkills sharing permissions.\u003c/strong\u003e Administrators can now control skills sharing and public sharing permissions per-group, matching the existing capabilities for tools, knowledge, and prompts. \u003ca href=\"https://github.com/open-webui/open-webui/commit/88401e91c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eLong content truncation in preview modals.\u003c/strong\u003e Citation and file content modals now truncate markdown-rendered content at 10,000 characters with a \u0026quot;Show all\u0026quot; expansion button, preventing UI jank when previewing very large documents.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eTranslation updates.\u003c/strong\u003e Translations for Spanish and German were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth session error handling.\u003c/strong\u003e Corrupted OAuth sessions are now gracefully handled and automatically cleaned up instead of causing errors. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7e224e4a536b07ec008613f06592e34050e7067c\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eTask model selector validation.\u003c/strong\u003e The task model selector in admin settings now correctly accepts models based on the new access grants system instead of rejecting all models with an incorrect error. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9a2595f0706d0c9d809ae7746001cf799f98db1d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eTool call message preservation.\u003c/strong\u003e Models no longer hallucinate tool outputs in multi-turn conversations because tool call history is now properly preserved instead of being merged into assistant messages. \u003ca href=\"https://github.com/open-webui/open-webui/discussions/21098\"\u003e#21098\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20600\"\u003e#20600\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f2aca781c87244cffc130aa2722e700c19a81d66\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool server startup initialization.\u003c/strong\u003e External tool servers configured via the \u0026quot;TOOL_SERVER_CONNECTIONS\u0026quot; environment variable now initialize automatically on startup, eliminating the need to manually visit the Admin Panel and save for tools to become available. This enables proper GitOps and containerized deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18140\"\u003e#18140\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/20914\"\u003e#20914\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f20cc6d7e6da493eb75ca1618f5cbd068fa57684\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e♻️ \u003cstrong\u003eResource handle cleanup.\u003c/strong\u003e File handles are now properly closed during audio transcription and pipeline uploads, preventing resource leaks that could cause system instability over time. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21411\"\u003e#21411\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⌨️ \u003cstrong\u003eStrikethrough shortcut conflict fix.\u003c/strong\u003e Pressing Ctrl+Shift+S to toggle the sidebar no longer causes text to become struck through in the chat input, by disabling the TipTap Strike extension's default keyboard shortcut when rich text mode is off. \u003ca href=\"https://github.com/open-webui/open-webui/commit/38ae91ae2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eTool call finish_reason fix.\u003c/strong\u003e API responses now correctly set finish_reason to \u0026quot;tool_calls\u0026quot; instead of \u0026quot;stop\u0026quot; when tool calls are present, fixing an issue where external API clients (such as OpenCode) would halt prematurely after tool execution when routing Ollama models through the Open WebUI API. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/20896\"\u003e#20896\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.8.1] - 2026-02-14\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eChannel user active status.\u003c/strong\u003e Checking user active status in channels is now faster thanks to optimized database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/ca6b18ab5cb94153a9dae233f975d36bf6b19b76\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eResponses API endpoint with model routing.\u003c/strong\u003e The OpenAI API proxy now supports a /responses endpoint that routes requests to the correct backend based on the model field in the request, instead of always using the first configured endpoint. This enables support for backends like vLLM that provide /skills and /v1/responses endpoints. \u003ca href=\"https://github.com/open-webui/open-webui/commit/abc9b63093d65f4d74342db85b7d5df1809aa0f0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/79ecbfc757f0642740d0e44fab98263d84295490\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eModel and prompt list optimization.\u003c/strong\u003e Improved performance when loading models and prompts by pre-fetching user group IDs once instead of making multiple database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/20de5a87da0c12e4052b50887a42ddd7228c5ef5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b8112d72b95e480f946f0688bed29321b61e65af\"\u003e\u003ccode\u003eb8112d7\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21507\"\u003e#21507\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/71ccedd2bf9cd6b831718cd556e74b4bb0633c4c\"\u003e\u003ccode\u003e71ccedd\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4225791313f003c85bdd7bd21e49879404359f3c\"\u003e\u003ccode\u003e4225791\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21458\"\u003e#21458\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e5cd1b479b641430ae53027af3648499aab836aa\"\u003e\u003ccode\u003ee5cd1b4\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/61d44aa773771127e1caa6c35cc322f8962adc13\"\u003e\u003ccode\u003e61d44aa\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ef036529b55c0e94c874dc6c16a2c0e5345dc542\"\u003e\u003ccode\u003eef03652\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e0bdef85abad22b01fe21ceeba96f1af4300cbed\"\u003e\u003ccode\u003ee0bdef8\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2ce935bdb10d2b26b230cd54cb649f5c667ed96a\"\u003e\u003ccode\u003e2ce935b\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/23b1e2cca475f2a6099c1d4d032b92dccc33f435\"\u003e\u003ccode\u003e23b1e2c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/05b8768fb9df2f079591f91fd544ad5793c793a5\"\u003e\u003ccode\u003e05b8768\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.43...v0.8.3\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.43\u0026new-version=0.8.3)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/darkhonor/helm-charts/pull/42","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/darkhonor%2Fhelm-charts/issues/42","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/42/packages"}},{"old_version":"0.7.2-slim","new_version":"0.8.1-slim","update_type":"minor","path":null,"pr_created_at":"2026-02-16T07:21:10.000Z","version_change":"0.7.2-slim → 0.8.1-slim","issue":{"uuid":"3946294355","node_id":"PR_kwDOPIpjyc7EBdRm","number":24,"state":"closed","title":"Bump open-webui/open-webui from 0.7.2-slim to 0.8.1-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2026-02-17T07:15:26.000Z","author_association":null,"state_reason":null,"created_at":"2026-02-16T07:21:10.000Z","updated_at":"2026-02-17T07:15:27.000Z","time_to_close":86056,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.7.2-slim","new_version":"0.8.1-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.7.2-slim to 0.8.1-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.8.1\u003c/h2\u003e\n\u003ch2\u003e[0.8.1] - 2026-02-14\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!CAUTION]\n⚠️ \u003cstrong\u003eDatabase Migrations\u003c/strong\u003e: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eChannel user active status.\u003c/strong\u003e Checking user active status in channels is now faster thanks to optimized database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/ca6b18ab5cb94153a9dae233f975d36bf6b19b76\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eResponses API endpoint with model routing.\u003c/strong\u003e The OpenAI API proxy now supports a /responses endpoint that routes requests to the correct backend based on the model field in the request, instead of always using the first configured endpoint. This enables support for backends like vLLM that provide /skills and /v1/responses endpoints. \u003ca href=\"https://github.com/open-webui/open-webui/commit/abc9b63093d65f4d74342db85b7d5df1809aa0f0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/79ecbfc757f0642740d0e44fab98263d84295490\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eModel and prompt list optimization.\u003c/strong\u003e Improved performance when loading models and prompts by pre-fetching user group IDs once instead of making multiple database queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/20de5a87da0c12e4052b50887a42ddd7228c5ef5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eBatch access control queries.\u003c/strong\u003e Improved performance when loading models, prompts, and knowledge bases by replacing multiple individual access checks with single batch queries, significantly reducing database load for large deployments. \u003ca href=\"https://github.com/open-webui/open-webui/commit/589c4e64c1b7bb7a7a5abc20382b92fb860e28c2\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 \u003cstrong\u003eFaster user list loading.\u003c/strong\u003e User lists now load significantly faster by deferring profile image loading; images are fetched separately in parallel by the browser, improving caching and reducing database load. \u003ca href=\"https://github.com/open-webui/open-webui/commit/b7549d2f6ca2843661ec79a5a1e55da9e7553368\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eWeb search result count.\u003c/strong\u003e The built-in search_web tool now respects the admin-configured \u0026quot;Search Result Count\u0026quot; setting instead of always returning 5 results when using Native Function Calling mode. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21373\"\u003e#21373\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21371\"\u003e#21371\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eSCIM externalId support.\u003c/strong\u003e SCIM-enabled deployments can now store and manage externalId for user provisioning, enabling better integration with identity providers like Microsoft Entra ID and Okta. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21099\"\u003e#21099\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21280\"\u003e#21280\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/d1d1efe212b16e0052359991d67fd813125077e8\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eTranslation updates.\u003c/strong\u003e Portuguese (Brazil) translations were updated.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003ePublic sharing security fix.\u003c/strong\u003e Fixed a security issue where users with write access could see the Public sharing option regardless of their actual public sharing permission, and direct API calls could bypass frontend sharing restrictions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21358\"\u003e#21358\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21356\"\u003e#21356\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eDirect model access control fix.\u003c/strong\u003e Model access control changes now persist correctly for direct Ollama and OpenAI models that don't have database entries, and error messages display properly instead of showing \u0026quot;[object Object]\u0026quot;. \u003ca href=\"https://github.com/open-webui/open-webui/commit/f027a01ab2ff3b6175af3dd13a4478c265c0544a\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21377\"\u003e#21377\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💭 \u003cstrong\u003eReasoning trace rendering performance.\u003c/strong\u003e Reasoning traces from models now render properly without being split into many fragments, preventing browser slowdowns during streaming responses. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21348\"\u003e#21348\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/3b61562c82448cf83710d8b6ed29b797991aa83a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eARM device compatibility fix.\u003c/strong\u003e Fixed an issue where upgrading to 0.8.0 would fail to start on ARM devices (like Raspberry Pi 4) due to torch 2.10.0 causing SIGILL errors; now pinned to torch\u0026lt;=2.9.1. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21385\"\u003e#21385\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21349\"\u003e#21349\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eSkills PostgreSQL compatibility fix.\u003c/strong\u003e Fixed a PostgreSQL compatibility issue where creating or listing skills would fail with a TypeError, while SQLite worked correctly. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21372\"\u003e#21372\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b4c3f54f9648c4232a0fd6557703ffa66fcf4caa\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21365\"\u003e#21365\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003ePostgreSQL analytics query fix.\u003c/strong\u003e Fixed an issue where retrieving chat IDs by model ID would fail on PostgreSQL due to incompatible DISTINCT ordering, while SQLite worked correctly. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21347\"\u003e#21347\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/7bda6bf767d5d5c4dc1111465096a88e10b5030e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗃️ \u003cstrong\u003eSQLite cascade delete fix.\u003c/strong\u003e Deleting chats now properly removes all associated messages in SQLite, matching PostgreSQL behavior and preventing orphaned data. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21362\"\u003e#21362\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ \u003cstrong\u003eOllama Cloud model naming fix.\u003c/strong\u003e Fixed an issue where using Ollama Cloud models would fail with \u0026quot;Model not found\u0026quot; errors because \u0026quot;:latest\u0026quot; was incorrectly appended to model names. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21386\"\u003e#21386\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eKnowledge selector tooltip z-index.\u003c/strong\u003e Fixed an issue where tooltips in the \u0026quot;Select Knowledge\u0026quot; dropdown were hidden behind the menu, making it difficult to read knowledge item names and descriptions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21375\"\u003e#21375\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u003cstrong\u003eModel selector scroll position.\u003c/strong\u003e The model selector dropdown now correctly scrolls to and centers the currently selected model when opened, and resets scroll position when reopened. \u003ca href=\"https://github.com/open-webui/open-webui/commit/0b05b2fc7ed4c38af158707438ff404d1beb7c91\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eSync modal unexpected appearance.\u003c/strong\u003e Fixed an issue where the Sync Modal would appear unexpectedly after enabling the \u0026quot;Community Sharing\u0026quot; feature if the user had previously visited the app with the sync parameter. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21376\"\u003e#21376\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eKnowledge collection layout fix.\u003c/strong\u003e Fixed a layout issue in the Knowledge integration menu where long collection names caused indentation artifacts and now properly truncate with ellipsis. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21374\"\u003e#21374\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eMetadata processing crash fix.\u003c/strong\u003e Fixed a latent bug where processing document metadata containing certain keys (content, pages, tables, paragraphs, sections, figures) would cause a RuntimeError due to dictionary mutation during iteration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21105\"\u003e#21105\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003ePassword validation regex fix.\u003c/strong\u003e Fixed the password validation regex by adding the raw string prefix, ensuring escape sequences like d and w are interpreted correctly. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/21400\"\u003e#21400\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21399\"\u003e#21399\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚠️ \u003cstrong\u003eDatabase Migrations:\u003c/strong\u003e This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.8.0\u003c/h2\u003e\n\u003ch2\u003e[0.8.0] - 2026-02-12\u003c/h2\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!CAUTION]\n⚠️ \u003cstrong\u003eDatabase Migrations\u003c/strong\u003e: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in production environments. If you are running a multi-worker, multi-server, or load-balanced deployment, all instances must be updated simultaneously, rolling updates are not supported and will cause application failures due to schema incompatibility.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!WARNING]\n⚠️ \u003cstrong\u003eLong-Running Database Migration\u003c/strong\u003e: This release includes a migration for the \u003ccode\u003echat_message\u003c/code\u003e table that can take a significant amount of time to complete, especially in larger deployments with extensive chat histories. Please plan for adequate downtime and allow the migration to finish completely without interruption.\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/883f1dda0f18fbe26aca7aed5a8804021a3685ca\"\u003e\u003ccode\u003e883f1dd\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21346\"\u003e#21346\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/12bad452fa409121effae088316fa2a29ae48541\"\u003e\u003ccode\u003e12bad45\u003c/code\u003e\u003c/a\u003e chore: Changelog updates (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21382\"\u003e#21382\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5de60dc922a74c9ce6cf5b2de3129e4ca3d9ffdd\"\u003e\u003ccode\u003e5de60dc\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a30b106ea3ac64a62ef3a3457689c402c833d6e5\"\u003e\u003ccode\u003ea30b106\u003c/code\u003e\u003c/a\u003e fix issues/21399 (\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/21400\"\u003e#21400\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d33ad462aa6f2105f0d118ab6f2fd74f693c8680\"\u003e\u003ccode\u003ed33ad46\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/3b61562c82448cf83710d8b6ed29b797991aa83a\"\u003e\u003ccode\u003e3b61562\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e5d88be4f3896f3407d762d4b2a24e0bb7447f06\"\u003e\u003ccode\u003ee5d88be\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b36f8d9314e2a127b88d521a53c804a7cdee4b48\"\u003e\u003ccode\u003eb36f8d9\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/626d236d137915aee090d8a82dc0a57fbc22424b\"\u003e\u003ccode\u003e626d236\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/79ecbfc757f0642740d0e44fab98263d84295490\"\u003e\u003ccode\u003e79ecbfc\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.7.2...v0.8.1\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.7.2-slim\u0026new-version=0.8.1-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/24","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/24","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/24/packages"}},{"old_version":"v0.6.36-slim","new_version":"v0.6.37-slim","update_type":"patch","path":null,"pr_created_at":"2025-11-24T07:27:53.000Z","version_change":"v0.6.36-slim → v0.6.37-slim","issue":{"uuid":"3657450130","node_id":"PR_kwDOPIpjyc61H4Jz","number":16,"state":"closed","title":"Bump open-webui/open-webui from v0.6.36-slim to v0.6.37-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-11-25T07:21:31.000Z","author_association":null,"state_reason":null,"created_at":"2025-11-24T07:27:53.000Z","updated_at":"2025-11-25T07:21:32.000Z","time_to_close":86018,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.6.36-slim","new_version":"v0.6.37-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.6.36-slim to v0.6.37-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.37\u003c/h2\u003e\n\u003ch2\u003e[0.6.37] - 2025-11-24\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔐 Granular sharing permissions are now available with two-tiered control separating group sharing from public sharing, allowing administrators to independently configure whether users can share workspace items with groups or make them publicly accessible, with separate permission toggles for models, knowledge bases, prompts, tools, and notes, configurable via \u0026quot;USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_SHARING\u0026quot;, \u0026quot;USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING\u0026quot;, and corresponding environment variables for other workspace item types, while groups can now be configured to opt-out of sharing via the \u0026quot;Allow Group Sharing\u0026quot; setting. \u003ca href=\"https://github.com/open-webui/open-webui/commit/7be750bcbb40da91912a0a66b7ab791effdcc3b6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f69e37a8507d6d57382d6670641b367f3127f90a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Password policy enforcement is now available with configurable validation rules, allowing administrators to require specific password complexity requirements via \u0026quot;ENABLE_PASSWORD_VALIDATION\u0026quot; and \u0026quot;PASSWORD_VALIDATION_REGEX_PATTERN\u0026quot; environment variables, with default pattern requiring minimum 8 characters including uppercase, lowercase, digit, and special character. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17794\"\u003e#17794\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Granular import and export permissions are now available for workspace items, introducing six separate permission toggles for models, prompts, and tools that are disabled by default for enhanced security. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19242\"\u003e#19242\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Default group assignment is now available for new users, allowing administrators to automatically assign newly registered users to a specified group for streamlined access control to models, prompts, and tools, particularly useful for organizations with group-based model access policies. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19325\"\u003e#19325\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17842\"\u003e#17842\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Password-based authentication can now be fully disabled via \u0026quot;ENABLE_PASSWORD_AUTH\u0026quot; environment variable, enforcing SSO-only authentication and preventing password login fallback when SSO is configured. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19113\"\u003e#19113\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ Large stream chunk handling was implemented to support models that generate images directly in their output responses, with configurable buffer size via \u0026quot;CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE\u0026quot; environment variable, resolving compatibility issues with models like Gemini 2.5 Flash Image. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18884\"\u003e#18884\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17626\"\u003e#17626\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ Streaming response middleware now handles images in delta updates with automatic base64 conversion, enabling proper display of images from models using the \u0026quot;choices[0].delta.images.image_url\u0026quot; format such as Gemini 2.5 Flash Image Preview on OpenRouter. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19073\"\u003e#19073\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19019\"\u003e#19019\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📈 Model list API performance was optimized by pre-fetching user group memberships and removing profile image URLs from response payloads, significantly reducing both database queries and payload size for instances with large model lists, with profile images now served dynamically via dedicated endpoints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19097\"\u003e#19097\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18950\"\u003e#18950\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⏩ Batch file processing performance was improved by reducing database queries by 67% while ensuring data consistency between vector and relational databases. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18953\"\u003e#18953\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🚀 Chat import performance was dramatically improved by replacing individual per-chat API requests with a bulk import endpoint, reducing import time by up to 95% for large chat collections and providing user feedback via toast notifications displaying the number of successfully imported chats. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17861\"\u003e#17861\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Socket event broadcasting performance was optimized by implementing user-specific rooms, significantly reducing server overhead particularly for users with multiple concurrent sessions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18996\"\u003e#18996\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ Weaviate is now supported as a vector database option, providing an additional choice for RAG document storage alongside existing ChromaDB, Milvus, Qdrant, and OpenSearch integrations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/14747\"\u003e#14747\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ PostgreSQL pgvector now supports HNSW index types and large dimensional embeddings exceeding 2000 dimensions through automatic halfvec type selection, with configurable index methods via \u0026quot;PGVECTOR_INDEX_METHOD\u0026quot;, \u0026quot;PGVECTOR_HNSW_M\u0026quot;, \u0026quot;PGVECTOR_HNSW_EF_CONSTRUCTION\u0026quot;, and \u0026quot;PGVECTOR_IVFFLAT_LISTS\u0026quot; environment variables. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19158\"\u003e#19158\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16890\"\u003e#16890\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Azure AI Search is now supported as a web search provider, enabling integration with Azure's cognitive search services via \u0026quot;AZURE_AI_SEARCH_API_KEY\u0026quot;, \u0026quot;AZURE_AI_SEARCH_ENDPOINT\u0026quot;, and \u0026quot;AZURE_AI_SEARCH_INDEX_NAME\u0026quot; configuration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19104\"\u003e#19104\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ External embedding generation now processes API requests in parallel instead of sequential batches, reducing document processing time by 10-50x when using OpenAI, Azure OpenAI, or Ollama embedding providers, with large PDFs now processing in seconds instead of minutes. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19296\"\u003e#19296\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💨 Base64 image conversion is now available for markdown content in chat responses, automatically uploading embedded images exceeding 1KB and replacing them with file URLs to reduce payload size and resource consumption, configurable via \u0026quot;REPLACE_IMAGE_URLS_IN_CHAT_RESPONSE\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19076\"\u003e#19076\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 OpenAI image generation now supports additional API parameters including quality settings for GPT Image 1, configurable via \u0026quot;IMAGES_OPENAI_API_PARAMS\u0026quot; environment variable or through the admin interface, enabling cost-effective image generation with low, medium, or high quality options. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19228\"\u003e#19228\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ Image editing can now be independently enabled or disabled via admin settings, allowing administrators to control whether sequential image prompts trigger image editing or new image generation, configurable via \u0026quot;ENABLE_IMAGE_EDIT\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19284\"\u003e#19284\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 SSRF protection was implemented with a configurable URL blocklist that prevents access to cloud metadata endpoints and private networks, with default protections for AWS, Google Cloud, Azure, and Alibaba Cloud metadata services, customizable via \u0026quot;WEB_FETCH_FILTER_LIST\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19201\"\u003e#19201\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Workspace models page now supports server-side pagination dramatically improving load times and usability for instances with large numbers of workspace models.\u003c/li\u003e\n\u003cli\u003e🔍 Hybrid search now indexes file metadata including filenames, titles, headings, sources, and snippets alongside document content, enabling keyword queries to surface documents where search terms appear only in metadata, configurable via \u0026quot;ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19095\"\u003e#19095\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📂 Knowledge base upload page now supports folder drag-and-drop with recursive directory handling, enabling batch uploads of entire directory structures instead of requiring individual file selection. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19320\"\u003e#19320\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🤖 Model cloning is now available in admin settings, allowing administrators to quickly create workspace models based on existing base models through a \u0026quot;Clone\u0026quot; option in the model dropdown menu. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17937\"\u003e#17937\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 UI scale adjustment is now available in interface settings, allowing users to increase the size of the entire interface from 1.0x to 1.5x for improved accessibility and readability, particularly beneficial for users with visual impairments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19186\"\u003e#19186\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📌 Default pinned models can now be configured by administrators for all new users, mirroring the behavior of default models where admin-configured defaults apply only to users who haven't customized their pinned models, configurable via \u0026quot;DEFAULT_PINNED_MODELS\u0026quot; environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19273\"\u003e#19273\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎙️ Text-to-Speech and Speech-to-Text services now receive user information headers when \u0026quot;ENABLE_FORWARD_USER_INFO_HEADERS\u0026quot; is enabled, allowing external TTS and STT providers to implement user-specific personalization, rate limiting, and usage tracking. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19323\"\u003e#19323\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19312\"\u003e#19312\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎙️ Voice mode now supports custom system prompts via \u0026quot;VOICE_MODE_PROMPT_TEMPLATE\u0026quot; configuration, allowing administrators to control response style and behavior for voice interactions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/18607\"\u003e#18607\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 WebSocket and Redis configuration options are now available including debug logging controls, custom ping timeout and interval settings, and arbitrary Redis connection options via \u0026quot;WEBSOCKET_SERVER_LOGGING\u0026quot;, \u0026quot;WEBSOCKET_SERVER_ENGINEIO_LOGGING\u0026quot;, \u0026quot;WEBSOCKET_SERVER_PING_TIMEOUT\u0026quot;, \u0026quot;WEBSOCKET_SERVER_PING_INTERVAL\u0026quot;, and \u0026quot;WEBSOCKET_REDIS_OPTIONS\u0026quot; environment variables. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19091\"\u003e#19091\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 MCP OAuth dynamic client registration now automatically detects and uses the appropriate token endpoint authentication method from server-supported options, enabling compatibility with OAuth servers that only support \u0026quot;client_secret_basic\u0026quot; instead of \u0026quot;client_secret_post\u0026quot;. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19193\"\u003e#19193\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 Custom headers can now be configured for remote MCP and OpenAPI tool server connections, enabling integration with services that require additional authentication headers. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/18918\"\u003e#18918\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Perplexity Search now supports custom API endpoints via \u0026quot;PERPLEXITY_SEARCH_API_URL\u0026quot; configuration and automatically forwards user information headers to enable personalized search experiences. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19147\"\u003e#19147\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 User information headers can now be optionally forwarded to external web search engines when \u0026quot;ENABLE_FORWARD_USER_INFO_HEADERS\u0026quot; is enabled. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19043\"\u003e#19043\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Daily active user metric is now available for monitoring, tracking unique users active since midnight UTC via the \u0026quot;webui.users.active.today\u0026quot; Prometheus gauge. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19236\"\u003e#19236\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19234\"\u003e#19234\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Audit log file path is now configurable via \u0026quot;AUDIT_LOGS_FILE_PATH\u0026quot; environment variable, enabling storage in separate volumes or custom locations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/19173\"\u003e#19173\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Sidebar collapse states for model lists and group information are now persistent across page refreshes, remembering user preferences through browser-based storage. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19159\"\u003e#19159\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Background image display was enhanced with semi-transparent overlays for navbar and sidebar, creating a seamless and visually cohesive design across the entire interface. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19157\"\u003e#19157\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📋 Tables in chat messages now include a copy button that appears on hover, enabling quick copying of table content alongside the existing CSV export functionality. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19162\"\u003e#19162\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Notes can now be created directly via the \u0026quot;/notes/new\u0026quot; URL endpoint with optional title and content query parameters, enabling faster note creation through bookmarks and shortcuts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19195\"\u003e#19195\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ Tag suggestions are now context-aware, displaying only relevant tags when creating or editing models versus chat conversations, preventing confusion between model and chat tags. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19135\"\u003e#19135\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✍️ Prompt autocompletion is now available independently of the rich text input setting, improving accessibility to the feature. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19150\"\u003e#19150\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Simplified Chinese, Traditional Chinese, Portuguese (Brazil), Catalan, Spanish (Spain), Finnish, Irish, Farsi, Swedish, Danish, German, Korean, and Thai were improved and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/fe6783c16699911c7be17392596d579333fb110c\"\u003e\u003ccode\u003efe6783c\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/19030\"\u003e#19030\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a91663c5041ef8ee48dd411619e65c9061c64d6e\"\u003e\u003ccode\u003ea91663c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1e01836c08585f0d969d360d8e95ab1e192bf4f6\"\u003e\u003ccode\u003e1e01836\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/97f5c214859df383317558c3999eaf3d5f67d891\"\u003e\u003ccode\u003e97f5c21\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9d14bc2a8dcaa228bd018c9b2d8dfca8e4e39f89\"\u003e\u003ccode\u003e9d14bc2\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4857c69bd304900869d793d3e57f5f7545108c6b\"\u003e\u003ccode\u003e4857c69\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/de889f5ec7963c4eca33dcba51e08b5a755b46f3\"\u003e\u003ccode\u003ede889f5\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0259312626dee07d505b5f6d4f8594198c2662a1\"\u003e\u003ccode\u003e0259312\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5af5e1d3e4e4e3f9d10e37d718a63efc00be54c7\"\u003e\u003ccode\u003e5af5e1d\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2e1ddf823b1c59d8ae968ab5ca264d42a64c9dc8\"\u003e\u003ccode\u003e2e1ddf8\u003c/code\u003e\u003c/a\u003e refac: prompt suggestions component\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.36...v0.6.37\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.6.36-slim\u0026new-version=v0.6.37-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/16","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/16","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/16/packages"}},{"old_version":"`2466939`","new_version":"`c77fa8d`","update_type":null,"path":null,"pr_created_at":"2025-10-01T22:15:59.000Z","version_change":"`2466939` → `c77fa8d`","issue":{"uuid":"2879842001","node_id":"PR_kwDONjNt7s6rpubR","number":8,"state":"open","title":"Bump open-webui/open-webui from `2466939` to `c77fa8d`","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-10-01T22:15:59.000Z","updated_at":"2025-10-01T22:15:59.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"`2466939`","new_version":"`c77fa8d`","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from `2466939` to `c77fa8d`.\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch1\u003eChangelog\u003c/h1\u003e\n\u003cp\u003eAll notable changes to this project will be documented in this file.\u003c/p\u003e\n\u003cp\u003eThe format is based on \u003ca href=\"https://keepachangelog.com/en/1.1.0/\"\u003eKeep a Changelog\u003c/a\u003e,\nand this project adheres to \u003ca href=\"https://semver.org/spec/v2.0.0.html\"\u003eSemantic Versioning\u003c/a\u003e.\u003c/p\u003e\n\u003ch2\u003e[0.6.32] - 2025-09-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ JSON model import moved to backend processing for significant performance improvements when importing large model files. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17871\"\u003e#17871\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚠️ Visual warnings for group permissions that display when a permission is disabled in a group but remains enabled in the default user role, clarifying inheritance behavior for administrators. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17848\"\u003e#17848\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ Milvus multi-tenancy mode using shared collections with resource ID filtering for improved scalability, mirroring the existing Qdrant implementation and configurable via ENABLE_MILVUS_MULTITENANCY_MODE environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17837\"\u003e#17837\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Enhanced tool result processing with improved error handling, better MCP tool result handling, and performance improvements for embedded UI components. \u003ca href=\"https://github.com/open-webui/open-webui/commit/4f06f29348b2c9d71c87d1bbe5b748a368f5101f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 New user groups now automatically inherit default group permissions, streamlining the admin setup process by eliminating manual permission configuration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17843\"\u003e#17843\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗂️ Bulk unarchive functionality for all chats, providing a single backend endpoint to efficiently restore all archived chats at once. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17857\"\u003e#17857\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ Browser tab title toggle setting allows users to control whether chat titles appear in the browser tab or display only \u0026quot;Open WebUI\u0026quot;. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17851\"\u003e#17851\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Reply-to-message functionality in channels, allowing users to reply directly to specific messages with visual threading and context display. \u003ca href=\"https://github.com/open-webui/open-webui/commit/1a18928c94903ad1f1f0391b8ade042c3e60205b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 Tool server import and export functionality, allowing direct upload of openapi.json and openapi.yaml files as an alternative to URL-based configuration. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14446\"\u003e#14446\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 User valve configuration for Functions is now available in the integration menu, providing consistent management alongside Tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17784\"\u003e#17784\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Admin permission toggle for controlling public sharing of notes, configurable via USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING environment variable. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17801\"\u003e#17801\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/715\"\u003e#715\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/715\"\u003eopen-webui/docs#715\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🗄️ DISKANN index type support for Milvus vector database with configurable maximum degree and search list size parameters. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17770\"\u003e#17770\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/docs/commit/cec50ab4d4b659558ca1ccd4b5e6fc024f05fb83\"\u003eDocs:Commit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Chinese (Simplified \u0026amp; Traditional) and Bosnian (Latin) were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛠️ MCP tool calls are now correctly routed to the appropriate server when multiple streamable-http MCP servers are enabled, preventing \u0026quot;Tool not found\u0026quot; errors. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17817\"\u003e#17817\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ External tool servers (OpenAPI/MCP) now properly process and return tool results to the model, restoring functionality that was broken in v0.6.31. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17764\"\u003e#17764\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔧 User valve detection now correctly identifies valves in imported tool code, ensuring gear icons appear in the integrations menu for all tools with user valves. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17765\"\u003e#17765\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 MCP OAuth discovery now correctly handles multi-tenant configurations by including subpaths in metadata URL discovery. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17768\"\u003e#17768\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ Milvus query operations now correctly use -1 instead of None for unlimited queries, preventing TypeError exceptions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17769\"\u003e#17769\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17088\"\u003e#17088\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 File upload error messages are now displayed when files are modified during upload, preventing user confusion on Android and Windows devices. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17777\"\u003e#17777\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 MessageInput Integrations button hover effect now displays correctly with proper visual feedback. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17767\"\u003e#17767\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 \u0026quot;Set as default\u0026quot; label positioning is fixed to ensure it remains clickable in all scenarios, including multi-model configurations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17779\"\u003e#17779\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎛️ Floating buttons now correctly retrieve message context by using the proper messageId parameter in createMessagesList calls. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17823\"\u003e#17823\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📌 Pinned chats are now properly cleared from the sidebar after archiving all chats, ensuring UI consistency without requiring a page refresh. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17832\"\u003e#17832\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗑️ Delete confirmation modals now properly truncate long names for Notes, Prompts, Tools, and Functions to prevent modal overflow. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17812\"\u003e#17812\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🌐 Internationalization function calls now use proper Svelte store subscription syntax, preventing \u0026quot;i18n.t is not a function\u0026quot; errors on the model creation page. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17819\"\u003e#17819\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Playground chat interface button layout is corrected to prevent vertical text rendering for Assistant/User role buttons. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17819\"\u003e#17819\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🏷️ UI text truncation is improved across multiple components including usernames in admin panels, arena model names, model tags, and filter tags to prevent layout overflow issues. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17805\"\u003e#17805\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17803\"\u003e#17803\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17791\"\u003e#17791\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17796\"\u003e#17796\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.31] - 2025-09-25\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔌 MCP (streamable HTTP) server support was added alongside existing OpenAPI server integration, allowing users to connect both server types through an improved server configuration interface. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15932\"\u003e#15932\u003c/a\u003e \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/16651\"\u003e#16651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/777e81f7a8aca957a359d51df8388e5af4721a68\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/de7f7b3d855641450f8e5aac34fbae0665e0b80e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1bbf3a91e4713039364b790e886e59b401572d0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c55afc42559c32a6f0c8beb0f1bb18e9360ab8af\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/61f20acf61f4fe30c0e5b0180949f6e1a8cf6524\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 To enable MCP server authentication, OAuth 2.1 dynamic client registration was implemented with secure automatic client registration, encrypted session management, and seamless authentication flows. \u003ca href=\"https://github.com/open-webui/open-webui/commit/972be4eda5a394c111e849075f94099c9c0dd9aa\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/77e971dd9fbeee806e2864e686df5ec75e82104b\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/879abd7feea3692a2f157da4a458d30f27217508\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/422d38fd114b1ebd8a7dbb114d64e14791e67d7a\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/709\"\u003e#709\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/709\"\u003eopen-webui/docs#709\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🛠️ External \u0026amp; Built-In Tools can now support rich UI element embedding (\u003ca href=\"https://docs.openwebui.com/features/plugin/tools/development\"\u003eDocs\u003c/a\u003e), allowing tools to return HTML content and interactive iframes that display directly within chat conversations with configurable security settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/07c5b25bc8b63173f406feb3ba183d375fedee6a\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a5d8882bba7933a2c2c31c0a1405aba507c370bb\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/7be5b7f50f498de97359003609fc5993a172f084\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a89ffccd7e96705a4a40e845289f4fcf9c4ae596\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003eSee full diff in \u003ca href=\"https://github.com/open-webui/open-webui/commits\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=main\u0026new-version=main)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/ArloL/open-webui-runner/pull/8","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArloL%2Fopen-webui-runner/issues/8","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/8/packages"}},{"old_version":"v0.6.30-slim","new_version":"0.6.31-slim","update_type":"patch","path":null,"pr_created_at":"2025-09-26T07:20:59.000Z","version_change":"v0.6.30-slim → 0.6.31-slim","issue":{"uuid":"2862841201","node_id":"PR_kwDOPIpjyc6qo31x","number":11,"state":"closed","title":"Bump open-webui/open-webui from v0.6.30-slim to 0.6.31-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":["rahulsalvi"],"locked":false,"comments_count":0,"pull_request":true,"closed_at":"2025-09-27T18:25:38.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-09-26T07:20:59.000Z","updated_at":"2025-09-27T18:25:38.000Z","time_to_close":126279,"merged_at":"2025-09-27T18:25:38.000Z","merged_by":"rahulsalvi","closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.6.30-slim","new_version":"0.6.31-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.6.30-slim to 0.6.31-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.31\u003c/h2\u003e\n\u003ch2\u003e[0.6.31] - 2025-09-25\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔌 MCP (streamable HTTP) server support was added alongside existing OpenAPI server integration, allowing users to connect both server types through an improved server configuration interface. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15932\"\u003e#15932\u003c/a\u003e \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/16651\"\u003e#16651\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/777e81f7a8aca957a359d51df8388e5af4721a68\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/de7f7b3d855641450f8e5aac34fbae0665e0b80e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f1bbf3a91e4713039364b790e886e59b401572d0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c55afc42559c32a6f0c8beb0f1bb18e9360ab8af\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/61f20acf61f4fe30c0e5b0180949f6e1a8cf6524\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 To enable MCP server authentication, OAuth 2.1 dynamic client registration was implemented with secure automatic client registration, encrypted session management, and seamless authentication flows. \u003ca href=\"https://github.com/open-webui/open-webui/commit/972be4eda5a394c111e849075f94099c9c0dd9aa\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/77e971dd9fbeee806e2864e686df5ec75e82104b\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/879abd7feea3692a2f157da4a458d30f27217508\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/422d38fd114b1ebd8a7dbb114d64e14791e67d7a\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/709\"\u003e#709\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/709\"\u003eopen-webui/docs#709\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🛠️ External \u0026amp; Built-In Tools can now support rich UI element embedding (\u003ca href=\"https://docs.openwebui.com/features/plugin/tools/development\"\u003eDocs\u003c/a\u003e), allowing tools to return HTML content and interactive iframes that display directly within chat conversations with configurable security settings. \u003ca href=\"https://github.com/open-webui/open-webui/commit/07c5b25bc8b63173f406feb3ba183d375fedee6a\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a5d8882bba7933a2c2c31c0a1405aba507c370bb\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/7be5b7f50f498de97359003609fc5993a172f084\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/a89ffccd7e96705a4a40e845289f4fcf9c4ae596\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Note editor now supports drag-and-drop reordering of list items with visual drag handles, making list organization more intuitive and efficient. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e4e97e727e9b4971f1c363b1280ca3a101599d88\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/aeb5288a3c7a6e9e0a47b807cc52f870c1b7dbe6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Search modal was enhanced with quick action buttons for starting new conversations and creating notes, with intelligent content pre-population from search queries. \u003ca href=\"https://github.com/open-webui/open-webui/commit/aa6f63a335e172fec1dc94b2056541f52c1167a6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/612a52d7bb7dbe9fa0bbbc8ac0a552d2b9801146\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b03529b006f3148e895b1094584e1ab129ecac5b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Tool user valve configuration interface was added to the integrations menu, displaying clickable gear icon buttons with tooltips for tools that support user-specific settings, making personal tool configurations easily accessible. \u003ca href=\"https://github.com/open-webui/open-webui/commit/27d61307cdce97ed11a05ec13fc300249d6022cd\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Channel access control was enhanced to require write permissions for posting, editing, and deleting messages, while read-only users can view content but cannot contribute. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17543\"\u003e#17543\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Channel models now support image processing, allowing AI assistants to view and analyze images shared in conversation threads. \u003ca href=\"https://github.com/open-webui/open-webui/commit/9f0010e234a6f40782a66021435d3c02b9c23639\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🌐 Attach Webpage button was added to the message input menu, providing a user-friendly modal interface for attaching web content and YouTube videos as an alternative to the existing URL syntax. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17534\"\u003e#17534\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Redis session storage support was added for OAuth redirects, providing better state handling in multi-pod Kubernetes deployments and resolving CSRF mismatch errors. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17223\"\u003e#17223\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15373\"\u003e#15373\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Ollama Cloud web search integration was added as a new search engine option, providing access to web search functionality through Ollama's cloud infrastructure. \u003ca href=\"https://github.com/open-webui/open-webui/commit/e06489d92baca095b8f376fbef223298c7772579\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4b6d34438bcfc45463dc7a9cb984794b32c1f0a1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/05c46008da85357dc6890b846789dfaa59f4a520\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fe65fe0b97ec5a8fff71592ff04a25c8e123d108\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/708\"\u003e#708\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/708\"\u003eopen-webui/docs#708\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🔍 Perplexity Websearch API integration was added as a new search engine option, providing access to the new websearch functionality provided by Perplexity. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17756\"\u003e#17756\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/7f411dd5cc1c29733216f79e99eeeed0406a2afe\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ OneDrive integration was improved to support separate client IDs for personal and business authentication, enabling both integrations to work simultaneously. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17619\"\u003e#17619\u003c/a\u003e, \u003ca href=\"https://docs.openwebui.com/tutorials/integrations/onedrive-sharepoint\"\u003eDocs\u003c/a\u003e, \u003ca href=\"https://docs.openwebui.com/getting-started/env-configuration/#onedrive\"\u003eDocs\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Pending user overlay content now supports markdown formatting, enabling rich text display for custom messages similar to banner functionality. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17681\"\u003e#17681\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Image generation model selection was centralized to enable dynamic model override in function calls, allowing pipes and tools to specify different models than the global default while maintaining backward compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17689\"\u003e#17689\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Interface design was modernized with updated visual styling, improved spacing, and refined component layouts across modals, sidebar, settings, and navigation elements. \u003ca href=\"https://github.com/open-webui/open-webui/commit/27a91cc80a24bda0a3a188bc3120a8ab57b00881\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/4ad743098615f9c58daa9df392f31109aeceeb16\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Notes query performance was optimized through database-level filtering and separated access control logic, reducing memory usage and eliminating N+1 query problems for better scalability. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17607\"\u003e#17607\u003c/a\u003e \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/da661756fa7eec754270e6dd8c67cbf74a28a17f\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Page loading performance was optimized by deferring API requests until components are actually opened, including ChangelogModal, ModelSelector, RecursiveFolder, ArchivedChatsModal, and SearchModal. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17542\"\u003e#17542\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17555\"\u003e#17555\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17557\"\u003e#17557\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17541\"\u003e#17541\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17640\"\u003e#17640\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Bundle size was reduced by 1.58MB through optimized highlight.js language support, improving page loading speed and reducing bandwidth usage. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17645\"\u003e#17645\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Editor collaboration functionality was refactored to reduce package size by 390KB and minimize compilation errors, improving build performance and reliability. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17593\"\u003e#17593\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e♿ Enhanced user interface accessibility through the addition of unique element IDs, improving targeting for testing, styling, and assistive technologies while providing better semantic markup for screen readers and accessibility tools. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17746\"\u003e#17746\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Chinese (Simplified and Traditional), Korean, Irish, Spanish, Finnish, French, Kabyle, Russian, and Catalan were enhanced and improved.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ SVG content security was enhanced by implementing DOMPurify sanitization to prevent XSS attacks through malicious SVG elements, ensuring safe rendering of user-generated SVG content. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/750a659a9fee7687e667d9d755e17b8a0c77d557\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ OneDrive attachment menu rendering issues were resolved by restructuring the submenu interface from dropdown to tabbed navigation, preventing menu items from being hidden or clipped due to overflow constraints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17554\"\u003e#17554\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17747/commits/90e4b49b881b644465831cc3028bb44f0f7a2196\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Attached conversation references now persist throughout the entire chat session, ensuring models can continue querying referenced conversations after multiple conversation turns. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17750\"\u003e#17750\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Search modal text box focus issues after pinning or unpinning chats were resolved, allowing users to properly exit the search interface by clicking outside the text box. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17743\"\u003e#17743\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Search function chat list is now properly updated in real-time when chats are created or deleted, eliminating stale search results and preview loading failures. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17741\"\u003e#17741\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Chat jitter and delayed code block expansion in multi-model sessions were resolved by reverting dynamic CodeEditor loading, restoring stable rendering behavior. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17715\"\u003e#17715\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17684\"\u003e#17684\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📎 File upload handling was improved to properly recognize uploaded files even when no accompanying text message is provided, resolving issues where attachments were ignored in custom prompts. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17492\"\u003e#17492\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Chat conversation referencing within projects was restored by including foldered chats in the reference menu, allowing users to properly quote conversations from within their project scope. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17530\"\u003e#17530\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 RAG query generation is now skipped when all attached files are set to full context mode, preventing unnecessary retrieval operations and improving system efficiency. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17744\"\u003e#17744\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 Memory leaks in file handling and HTTP connections are prevented through proper resource cleanup, ensuring stable memory usage during large file downloads and processing operations. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17608\"\u003e#17608\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 OAuth access token refresh errors are resolved by properly implementing async/await patterns, preventing \u0026quot;coroutine object has no attribute get\u0026quot; failures during token expiry. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17585\"\u003e#17585\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17678\"\u003e#17678\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚙️ Valve behavior was improved to properly handle default values and array types, ensuring only explicitly set values are persisted while maintaining consistent distinction between custom and default valve states. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17664\"\u003e#17664\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔍 Hybrid search functionality was enhanced to handle inconsistent parameter types and prevent failures when collection results are None, empty, or in unexpected formats. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17617\"\u003e#17617\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 Empty folder deletion is now allowed regardless of chat deletion permission restrictions, resolving cases where users couldn't remove folders after deleting all contained chats. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17683\"\u003e#17683\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📝 Rich text editor console errors were resolved by adding proper error handling when the TipTap editor view is not available or not yet mounted. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17697\"\u003e#17697\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗒️ Hidden models are now properly excluded from the notes section dropdown and default model selection, preventing users from accessing models they shouldn't see. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17722\"\u003e#17722\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ AI-generated image download filenames now use a clean, translatable \u0026quot;Generated Image\u0026quot; format instead of potentially problematic response text, improving file management and compatibility. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17721\"\u003e#17721\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Toggle switch display issues in the Integrations interface are fixed, preventing background highlighting and obscuring on hover. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17564\"\u003e#17564\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/598282cf75de358215d045c617e70d28bc48929e\"\u003e\u003ccode\u003e598282c\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17747\"\u003e#17747\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f7ea60b500b589ca95f32d5e6997481f796786a4\"\u003e\u003ccode\u003ef7ea60b\u003c/code\u003e\u003c/a\u003e Update CHANGELOG.md\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2fa222d00a8120e5813b2efb2f2089f6c1fbde49\"\u003e\u003ccode\u003e2fa222d\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/6920fed97e805224e94c6ecdeb80bc91efebfb76\"\u003e\u003ccode\u003e6920fed\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/528e58155b5cb4f55e138efb8d153881c667d1c5\"\u003e\u003ccode\u003e528e581\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/503fc354cc70d56888057f629fff6ee9d6c7de19\"\u003e\u003ccode\u003e503fc35\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17752\"\u003e#17752\u003c/a\u003e from Classic298/changelog-done\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4eec423950e722df6fdfb5145fb101e64225a0e0\"\u003e\u003ccode\u003e4eec423\u003c/code\u003e\u003c/a\u003e Update CHANGELOG.md\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/52bc5306b02002d66fc4066277b74dc799379b0f\"\u003e\u003ccode\u003e52bc530\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/90e4b49b881b644465831cc3028bb44f0f7a2196\"\u003e\u003ccode\u003e90e4b49\u003c/code\u003e\u003c/a\u003e refac/fix: onedrive input menu styling issue\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/750a659a9fee7687e667d9d755e17b8a0c77d557\"\u003e\u003ccode\u003e750a659\u003c/code\u003e\u003c/a\u003e security: svg xss fix\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.30...v0.6.31\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.6.30-slim\u0026new-version=0.6.31-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/11","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/11","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/11/packages"}},{"old_version":"0.6.26-slim","new_version":"v0.6.28-slim","update_type":"patch","path":null,"pr_created_at":"2025-09-11T07:23:36.000Z","version_change":"0.6.26-slim → v0.6.28-slim","issue":{"uuid":"2817956206","node_id":"PR_kwDOPIpjyc6n9plu","number":9,"state":"closed","title":"Bump open-webui/open-webui from 0.6.26-slim to v0.6.28-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":"2025-09-14T22:42:09.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-09-11T07:23:36.000Z","updated_at":"2025-09-14T22:42:09.000Z","time_to_close":314313,"merged_at":"2025-09-14T22:42:09.000Z","merged_by":"rahulsalvi","closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.26-slim","new_version":"v0.6.28-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.26-slim to v0.6.28-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.28\u003c/h2\u003e\n\u003ch2\u003e[0.6.28] - 2025-09-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔍 The \u0026quot;@\u0026quot; command for model selection now supports real-time search and filtering, improving usability and aligning its behavior with other input commands. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17307\"\u003e#17307\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f2a09c71499489ee71599af4a179e7518aaf658b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ External tool server data handling is now more robust, automatically attempting to parse specifications as JSON before falling back to YAML, regardless of the URL extension. \u003ca href=\"https://github.com/open-webui/open-webui/commit/774c0056bde88ed4831422efa81506488e3d6641\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎯 The \u0026quot;Title\u0026quot; field is now automatically focused when creating a new chat folder, streamlining the folder creation process. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17315\"\u003e#17315\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/c51a651a2d5e2a27546416666812e9b92205562d\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Brazilian Portuguese and Simplified Chinese translations were expanded and refined.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔊 A regression affecting Text-to-Speech for local providers using the OpenAI engine was fixed by reverting a URL joining change. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17316\"\u003e#17316\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8339f59cdfc63f2d58c8e26933d1bf1438479d75\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🪧 A regression was fixed where the input modal for prompts with placeholders would not open, causing the raw prompt text to be pasted into the chat input field instead. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17325\"\u003e#17325\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/d5cb65527eaa4831459a4c7dbf187daa9c0525ae\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔑 An issue was resolved where modified connection keys in the OpenAIConnection component did not take effect. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17324\"\u003e#17324\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.27\u003c/h2\u003e\n\u003ch2\u003e[0.6.27] - 2025-09-09\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📁 Emoji folder icons were added, allowing users to personalize workspace organization with visual cues, including improved chevron display. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1588f42fe777ad5d807e3f2fc8dbbc47a8db87c0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b70c0f36c0f5bbfc2a767429984d6fba1a7bb26c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/11dea8795bfce42aa5d8d58ef316ded05173bd87\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c0a47169fa059154d5f5a9ea6b94f9a66d82f255\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 The 'Search Collection' input field now dynamically displays the total number of files within the knowledge base. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/fbbe1117ae4c9c8fec6499d790eee275818eccc5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ A provider toggle in connection settings now allows users to manually specify Azure OpenAI deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/5bdd334b74fbd154085f2d590f4afdba32469c8a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Model list caching performance was optimized by fixing cache key generation to reduce redundant API calls. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17158\"\u003e#17158\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Azure OpenAI image generation is now supported, with configurations for IMAGES_OPENAI_API_VERSION via environment variable and admin UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17147\"\u003e#17147\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/16274\"\u003e#16274\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/679\"\u003e#679\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/679\"\u003eopen-webui/docs#679\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e⚡ Comprehensive N+1 query performance is optimized by reducing database queries from 1+N to 1+1 patterns across major listing endpoints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17165\"\u003e#17165\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17160\"\u003e#17160\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17161\"\u003e#17161\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17162\"\u003e#17162\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17159\"\u003e#17159\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17166\"\u003e#17166\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The PDF.js library is now dynamically loaded, significantly reducing initial page load size and improving responsiveness. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17222\"\u003e#17222\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The heic2any library is now dynamically loaded across various message input components, including channels, for faster page loads. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17225\"\u003e#17225\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17229\"\u003e#17229\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📚 The knowledge API now supports a \u0026quot;delete_file\u0026quot; query parameter, allowing configurable file deletion behavior. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/22c4ef4fb096498066b73befe993ae3a82f7a8e7\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Llama.cpp timing statistics are now integrated into the usage field for comprehensive model performance metrics. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/e830b4959ecd4b2795e29e53026984a58a7696a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ The PGVECTOR_CREATE_EXTENSION environment variable now allows control over automatic pgvector extension creation. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c2b4976c82d335ed524bd80dc914b5e2f5bfbd9e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b45219c8b15b48d5ee3d42983e1107bbcefbab01\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/672\"\u003e#672\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/672\"\u003eopen-webui/docs#672\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🔒 Comprehensive server-side OAuth token management was implemented, securely storing encrypted tokens in a new database table and introducing an automatic refresh mechanism, enabling seamless and secure forwarding of valid user-specific OAuth tokens to downstream services, including OpenAI-compatible endpoints and external tool servers via the new \u0026quot;system_oauth\u0026quot; authentication type, resolving long-standing issues such as large token size limitations, stale/expired tokens, and reliable token propagation, and enhancing overall security by minimizing client-side token exposure, configurable via \u0026quot;ENABLE_OAUTH_ID_TOKEN_COOKIE\u0026quot; and \u0026quot;OAUTH_SESSION_TOKEN_ENCRYPTION_KEY\u0026quot; environment variables. [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/683\"\u003e#683\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/683\"\u003eopen-webui/docs#683\u003c/a\u003e), \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17210\"\u003e#17210\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/8957\"\u003e#8957\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/11029\"\u003e#11029\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17178\"\u003e#17178\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17183\"\u003e#17183\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/217f4daef09b36d3d4cc4681e11d3ebd9984a1a5\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fc11e4384fe98fac659e10596f67c23483578867\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f11bdc6ab5dd5682bb3e27166e77581f5b8af3e0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f71834720e623761d972d4d740e9bbd90a3a86c6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b5bb6ae177dcdc4e8274d7e5ffa50bc8099fd466\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b786d1e3f3308ef4f0f95d7130ddbcaaca4fc927\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8a9f8627017bd0a74cbd647891552b26e56aabb7\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/30d1dc2c60e303756120fe1c5538968c4e6139f4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/2b2d123531eb3f42c0e940593832a64e2806240d\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/6f6412dd16c63c2bb4df79a96b814bf69cb3f880\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Conditional Permission Hardening for OpenShift Deployments: Added a build argument to enable optional permission hardening for OpenShift and container environments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0ebe4f8f8490451ac8e85a4846f010854d9b54e5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Regex pattern support is added for OAuth blocked groups, allowing more flexible group filtering rules. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/df66e21472646648d008ebb22b0e8d5424d491df\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Web search result display was enhanced to include titles and favicons, providing a clearer overview of search sources. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/33f04a771455e3fabf8f0e8ebb994ae7f41b8ed4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0a85dd4bca23022729eafdbc82c8c139fa365af2\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/16090bc2721fde492afa2c4af5927e2b668527e1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17197\"\u003e#17197\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14179\"\u003e#14179\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1cdb7aed1ee9bf81f2fd0404be52dcfa64f8ed4f\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/f2525ebc447c008cf7269ef20ce04fa456f302c4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/7f523de408ede4075349d8de71ae0214b7e1a62e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/3d37e4a42d344051ae715ab59bd7b5718e46c343\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/cd5e2be27b613314aadda6107089331783987985\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/6dc0df247347aede2762fe2065cf30275fd137ae\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 A new setting was added to control whether clicking a suggested prompt automatically sends the message or only inserts the text. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17192\"\u003e#17192\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e023a98f11fc52feb21e4065ec707cc98e50c7d3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, Catalan, and Spanish were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔍 Hybrid search functionality now correctly handles lexical-semantic weight labels and avoids errors when BM25 weight is zero. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17049\"\u003e#17049\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17046\"\u003e#17046\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛑 Task stopping errors are prevented by gracefully handling multiple stop requests for the same task. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17195\"\u003e#17195\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐍 Code execution package detection precision is improved in Pyodide to prevent unnecessary package inclusions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/bbe116795860a81a647d9567e0d9cb1950650095\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Tool message format API compliance is fixed by ensuring content fields in tool call responses contain valid string values instead of null. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/37bf0087e5b8a324009c9d06b304027df351ea6b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📱 Mobile app config API authentication now supports Authorization header token verification with cookie fallback for iOS and Android requests. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17175\"\u003e#17175\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 Knowledge file save race conditions are prevented by serializing API calls and adding an \u0026quot;isSaving\u0026quot; guard. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17137\"\u003e#17137\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/4ca936f0bf9813bee11ec8aea41d7e34fb6b16a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 The SSO login button visibility is restored for OIDC PKCE authentication without a client secret. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17012\"\u003e#17012\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/171021cfa4276f63fd9fd7f31fa0c904fb13c24c\"\u003e\u003ccode\u003e171021c\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17327\"\u003e#17327\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d3d7b209b2aa156eadd65f69d79984c205f58aee\"\u003e\u003ccode\u003ed3d7b20\u003c/code\u003e\u003c/a\u003e refac: changelog styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/6ddbb41aac69bcee68bf72566c338aa56cdbd1ca\"\u003e\u003ccode\u003e6ddbb41\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17333\"\u003e#17333\u003c/a\u003e from Classic298/patch-2\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2a9925fe18dc3e022ff662918965dd3ac1c52da0\"\u003e\u003ccode\u003e2a9925f\u003c/code\u003e\u003c/a\u003e Update CHANGELOG.md\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/81e401a520179484cffa2ace80c25955b08de7d3\"\u003e\u003ccode\u003e81e401a\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ba432090c5261bc4f193c9eb8bb84be0ad269bd6\"\u003e\u003ccode\u003eba43209\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17320\"\u003e#17320\u003c/a\u003e from ShirasawaSama/patch-16\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/de634a7599f6340db55137213d0eba7c481228ca\"\u003e\u003ccode\u003ede634a7\u003c/code\u003e\u003c/a\u003e chore: dep bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/803daebfe4f2986d741a9654725c3371e23ef71d\"\u003e\u003ccode\u003e803daeb\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/958a76d448b69a8e7720ae1743246ca3c545ee0b\"\u003e\u003ccode\u003e958a76d\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2dd0eaad738a77b70051c690402891e12251261b\"\u003e\u003ccode\u003e2dd0eaa\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17328\"\u003e#17328\u003c/a\u003e from open-webui/main\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.26...v0.6.28\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.26-slim\u0026new-version=v0.6.28-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/9","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/9","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/9/packages"}},{"old_version":"0.6.26-slim","new_version":"v0.6.27-slim","update_type":"patch","path":null,"pr_created_at":"2025-09-10T07:23:04.000Z","version_change":"0.6.26-slim → v0.6.27-slim","issue":{"uuid":"2814456821","node_id":"PR_kwDOPIpjyc6nwTP1","number":8,"state":"open","title":"Bump open-webui/open-webui from 0.6.26-slim to v0.6.27-slim","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-09-10T07:23:04.000Z","updated_at":"2025-09-10T07:23:05.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.26-slim","new_version":"v0.6.27-slim","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.26-slim to v0.6.27-slim.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.27\u003c/h2\u003e\n\u003ch2\u003e[0.6.27] - 2025-09-09\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📁 Emoji folder icons were added, allowing users to personalize workspace organization with visual cues, including improved chevron display. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1588f42fe777ad5d807e3f2fc8dbbc47a8db87c0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b70c0f36c0f5bbfc2a767429984d6fba1a7bb26c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/11dea8795bfce42aa5d8d58ef316ded05173bd87\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c0a47169fa059154d5f5a9ea6b94f9a66d82f255\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 The 'Search Collection' input field now dynamically displays the total number of files within the knowledge base. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/fbbe1117ae4c9c8fec6499d790eee275818eccc5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e☁️ A provider toggle in connection settings now allows users to manually specify Azure OpenAI deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/5bdd334b74fbd154085f2d590f4afdba32469c8a\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ Model list caching performance was optimized by fixing cache key generation to reduce redundant API calls. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17158\"\u003e#17158\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Azure OpenAI image generation is now supported, with configurations for IMAGES_OPENAI_API_VERSION via environment variable and admin UI. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17147\"\u003e#17147\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/16274\"\u003e#16274\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/679\"\u003e#679\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/679\"\u003eopen-webui/docs#679\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e⚡ Comprehensive N+1 query performance is optimized by reducing database queries from 1+N to 1+1 patterns across major listing endpoints. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17165\"\u003e#17165\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17160\"\u003e#17160\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17161\"\u003e#17161\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17162\"\u003e#17162\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17159\"\u003e#17159\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17166\"\u003e#17166\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The PDF.js library is now dynamically loaded, significantly reducing initial page load size and improving responsiveness. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17222\"\u003e#17222\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e⚡ The heic2any library is now dynamically loaded across various message input components, including channels, for faster page loads. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17225\"\u003e#17225\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17229\"\u003e#17229\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📚 The knowledge API now supports a \u0026quot;delete_file\u0026quot; query parameter, allowing configurable file deletion behavior. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/22c4ef4fb096498066b73befe993ae3a82f7a8e7\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📊 Llama.cpp timing statistics are now integrated into the usage field for comprehensive model performance metrics. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/e830b4959ecd4b2795e29e53026984a58a7696a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🗄️ The PGVECTOR_CREATE_EXTENSION environment variable now allows control over automatic pgvector extension creation. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/c2b4976c82d335ed524bd80dc914b5e2f5bfbd9e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/b45219c8b15b48d5ee3d42983e1107bbcefbab01\"\u003eCommit\u003c/a\u003e, [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/672\"\u003e#672\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/672\"\u003eopen-webui/docs#672\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e🔒 Comprehensive server-side OAuth token management was implemented, securely storing encrypted tokens in a new database table and introducing an automatic refresh mechanism, enabling seamless and secure forwarding of valid user-specific OAuth tokens to downstream services, including OpenAI-compatible endpoints and external tool servers via the new \u0026quot;system_oauth\u0026quot; authentication type, resolving long-standing issues such as large token size limitations, stale/expired tokens, and reliable token propagation, and enhancing overall security by minimizing client-side token exposure, configurable via \u0026quot;ENABLE_OAUTH_ID_TOKEN_COOKIE\u0026quot; and \u0026quot;OAUTH_SESSION_TOKEN_ENCRYPTION_KEY\u0026quot; environment variables. [Docs:\u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/683\"\u003e#683\u003c/a\u003e](\u003ca href=\"https://redirect.github.com/open-webui/docs/pull/683\"\u003eopen-webui/docs#683\u003c/a\u003e), \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17210\"\u003e#17210\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/8957\"\u003e#8957\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/discussions/11029\"\u003e#11029\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17178\"\u003e#17178\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17183\"\u003e#17183\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/217f4daef09b36d3d4cc4681e11d3ebd9984a1a5\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/fc11e4384fe98fac659e10596f67c23483578867\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f11bdc6ab5dd5682bb3e27166e77581f5b8af3e0\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f71834720e623761d972d4d740e9bbd90a3a86c6\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b5bb6ae177dcdc4e8274d7e5ffa50bc8099fd466\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/b786d1e3f3308ef4f0f95d7130ddbcaaca4fc927\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/8a9f8627017bd0a74cbd647891552b26e56aabb7\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/30d1dc2c60e303756120fe1c5538968c4e6139f4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/2b2d123531eb3f42c0e940593832a64e2806240d\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/6f6412dd16c63c2bb4df79a96b814bf69cb3f880\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Conditional Permission Hardening for OpenShift Deployments: Added a build argument to enable optional permission hardening for OpenShift and container environments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0ebe4f8f8490451ac8e85a4846f010854d9b54e5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e👥 Regex pattern support is added for OAuth blocked groups, allowing more flexible group filtering rules. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/df66e21472646648d008ebb22b0e8d5424d491df\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Web search result display was enhanced to include titles and favicons, providing a clearer overview of search sources. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/33f04a771455e3fabf8f0e8ebb994ae7f41b8ed4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/0a85dd4bca23022729eafdbc82c8c139fa365af2\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/16090bc2721fde492afa2c4af5927e2b668527e1\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17197\"\u003e#17197\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14179\"\u003e#14179\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1cdb7aed1ee9bf81f2fd0404be52dcfa64f8ed4f\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/f2525ebc447c008cf7269ef20ce04fa456f302c4\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/7f523de408ede4075349d8de71ae0214b7e1a62e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/3d37e4a42d344051ae715ab59bd7b5718e46c343\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/cd5e2be27b613314aadda6107089331783987985\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/6dc0df247347aede2762fe2065cf30275fd137ae\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 A new setting was added to control whether clicking a suggested prompt automatically sends the message or only inserts the text. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17192\"\u003e#17192\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/e023a98f11fc52feb21e4065ec707cc98e50c7d3\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.\u003c/li\u003e\n\u003cli\u003e🌐 Translations for Portuguese (Brazil), Simplified Chinese, Catalan, and Spanish were enhanced and expanded.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔍 Hybrid search functionality now correctly handles lexical-semantic weight labels and avoids errors when BM25 weight is zero. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17049\"\u003e#17049\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17046\"\u003e#17046\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛑 Task stopping errors are prevented by gracefully handling multiple stop requests for the same task. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17195\"\u003e#17195\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🐍 Code execution package detection precision is improved in Pyodide to prevent unnecessary package inclusions. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/bbe116795860a81a647d9567e0d9cb1950650095\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛠️ Tool message format API compliance is fixed by ensuring content fields in tool call responses contain valid string values instead of null. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/37bf0087e5b8a324009c9d06b304027df351ea6b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📱 Mobile app config API authentication now supports Authorization header token verification with cookie fallback for iOS and Android requests. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17175\"\u003e#17175\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💾 Knowledge file save race conditions are prevented by serializing API calls and adding an \u0026quot;isSaving\u0026quot; guard. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17137\"\u003e#17137\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/4ca936f0bf9813bee11ec8aea41d7e34fb6b16a9\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 The SSO login button visibility is restored for OIDC PKCE authentication without a client secret. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17012\"\u003e#17012\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔊 Text-to-Speech (TTS) API requests now use proper URL joining methods, ensuring reliable functionality regardless of trailing slashes in the base URL. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17061\"\u003e#17061\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🛡️ Admin account creation on Hugging Face Spaces now correctly detects the configured port, resolving issues with custom port deployments. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17064\"\u003e#17064\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 Unicode filename support is improved for external document loaders by properly URL-encoding filenames in HTTP headers. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17013\"\u003e#17013\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17000\"\u003e#17000\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔗 Web page and YouTube attachments are now correctly processed by setting their type as \u0026quot;text\u0026quot; and using collection names for accurate content retrieval. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/487979859a6ffcfd60468f523822cdf838fbef5b\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e✍️ Message input composition event handling is fixed to properly manage text input for multilingual users using Input Method Editors (IME). \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17085\"\u003e#17085\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Follow-up tooltip duplication is removed, streamlining the user interface and preventing visual clutter. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17186\"\u003e#17186\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🎨 Chat button text display is corrected by preventing clipping of descending characters and removing unnecessary capitalization. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17191\"\u003e#17191\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🧠 RAG Loop/Error with Gemma 3.1 2B Instruct is fixed by correctly unwrapping unexpected single-item list responses from models. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/1bc9711afd2b72cd07c4e539a83783868733767c\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17213\"\u003e#17213\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🖼️ HEIC conversion failures are resolved, improving robustness of image handling. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17225\"\u003e#17225\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📦 The slim Docker image size regression has been fixed by refining the build process to correctly exclude components when USE_SLIM=true. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16997\"\u003e#16997\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/be373e9fd42ac73b0302bdb487e16dbeae178b4e\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/0ebe4f8f8490451ac8e85a4846f010854d9b54e5\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e📁 Knowledge base update validation errors are resolved, ensuring seamless management via UI or API. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17244\"\u003e#17244\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/9aac1489080a5c9441e89b1a56de0d3a672bc5fb\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Resolved a security issue where a global web search setting overrode model-specific restrictions, ensuring model-level settings are now correctly prioritized. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17151\"\u003e#17151\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/9368d0ac751ec3072d5a96712b80a9b20a642ce6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 OAuth redirect reliability is improved by robustly preserving the intended redirect path using session storage. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17235\"\u003e#17235\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/4f2b821088367da18374027919594365c7a3f459\"\u003eCommit\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/15575\"\u003e#15575\u003c/a\u003e, \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/d9f97c832c556fae4b116759da0177bf4fe619de\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔐 Fixed a security vulnerability where knowledge base access within chat folders persisted after permissions were revoked. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17182\"\u003e#17182\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/40e40d1dddf9ca937e99af41c8ca038dbc93a7e6\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 OIDC access denied errors are now displayed as user-friendly toast notifications instead of raw JSON. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17208\"\u003e#17208\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/3d6d050ad82d360adc42d6e9f42e8faf8d13c9f4\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e💬 Chat exception handling is enhanced to prevent system instability during message generation and ensure graceful error recovery. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17070/commits/f56889c5c7f0cf1a501c05d35dfa614e4f8b6958\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e🔒 Static asset authentication is improved by adding crossorigin=\u0026quot;use-credentials\u0026quot; attributes to all link elements, enabling proper cookie forwarding for proxy environments and authenticated requests to favicon, manifest, and stylesheet resources. \u003ca href=\"https://redirect.github.com/open-webui/open-webui/pull/17280\"\u003e#17280\u003c/a\u003e, \u003ca href=\"https://github.com/open-webui/open-webui/commit/f17d8b5d19e1a05df7d63f53e939c99772a59c1e\"\u003eCommit\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/918f507d8cdc652ae913b8596877a8a50b845114\"\u003e\u003ccode\u003e918f507\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17070\"\u003e#17070\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f7e85cd0bfa4efc66cbe7e7ec19deecc981c203f\"\u003e\u003ccode\u003ef7e85cd\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4b4583df6280437ff208905d7dcc0c96d979f090\"\u003e\u003ccode\u003e4b4583d\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/bcf76dfa74b98b82fd4a2c9a47292b174b1a84c0\"\u003e\u003ccode\u003ebcf76df\u003c/code\u003e\u003c/a\u003e refac: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/485392fe63fe488100dc2c1086cdd9b4980362e2\"\u003e\u003ccode\u003e485392f\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/cbb4684b169fc89bb30a60b199158a6a6a170957\"\u003e\u003ccode\u003ecbb4684\u003c/code\u003e\u003c/a\u003e chore\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0531ca6530d1f63dcf348e65bb0367de93499898\"\u003e\u003ccode\u003e0531ca6\u003c/code\u003e\u003c/a\u003e refac/fix\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/32cb9df3c49155f2e625672a806f1afe7fa1e3fb\"\u003e\u003ccode\u003e32cb9df\u003c/code\u003e\u003c/a\u003e refac/enh: knowledge ac backend validation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/71fd483fba2d8828cdc46298ce702d77d16d7203\"\u003e\u003ccode\u003e71fd483\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/17276\"\u003e#17276\u003c/a\u003e from Elettrotecnica/extend-docling-configuration\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/63f38c584f8e5297490dd446364712fa17f7e869\"\u003e\u003ccode\u003e63f38c5\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.26...v0.6.27\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.26-slim\u0026new-version=v0.6.27-slim)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/8","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/8","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/8/packages"}},{"old_version":"0.6.22","new_version":"0.6.25","update_type":"patch","path":null,"pr_created_at":"2025-08-25T13:44:21.000Z","version_change":"0.6.22 → 0.6.25","issue":{"uuid":"3351926904","node_id":"PR_kwDOPIpjyc6lN-Ea","number":6,"state":"open","title":"Bump open-webui/open-webui from 0.6.22 to 0.6.25","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-08-25T13:44:21.000Z","updated_at":"2025-08-28T17:21:22.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.22","new_version":"0.6.25","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.22 to 0.6.25.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.25\u003c/h2\u003e\n\u003ch2\u003e[0.6.25] - 2025-08-22\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Generation Reliability Restored\u003c/strong\u003e: Fixed a key issue causing image generation failures.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eReranking Functionality Restored\u003c/strong\u003e: Resolved errors with rerank feature.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.24\u003c/h2\u003e\n\u003ch2\u003e[0.6.24] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e♿ \u003cstrong\u003eHigh Contrast Mode in Chat Messages\u003c/strong\u003e: Implemented enhanced High Contrast Mode support for chat messages, making text and important details easier to read and improving accessibility for users with visual preferences or requirements.\u003c/li\u003e\n\u003cli\u003e🌎 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Enhanced and expanded translations for a more natural and professional user experience for speakers of these languages across the entire interface.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eComfyUI Image Generation Restored\u003c/strong\u003e: Fixed a critical bug where ComfyUI-based image generation was not functioning, ensuring users can once again effortlessly create and interact with AI-generated visuals in their workflows.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTool Server Loading and Visibility Restored\u003c/strong\u003e: Resolved an issue where connected tool servers were not loading or visible, restoring seamless integration and uninterrupted access to all external and custom tools directly within the platform.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis User Session Reliability\u003c/strong\u003e: Fixed a problem affecting the saving of user sessions in Redis, ensuring reliable login sessions, stable authentication, and secure multi-user environments.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.23\u003c/h2\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.25] - 2025-08-22\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Generation Reliability Restored\u003c/strong\u003e: Fixed a key issue causing image generation failures.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eReranking Functionality Restored\u003c/strong\u003e: Resolved errors with rerank feature.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.24] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e♿ \u003cstrong\u003eHigh Contrast Mode in Chat Messages\u003c/strong\u003e: Implemented enhanced High Contrast Mode support for chat messages, making text and important details easier to read and improving accessibility for users with visual preferences or requirements.\u003c/li\u003e\n\u003cli\u003e🌎 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Enhanced and expanded translations for a more natural and professional user experience for speakers of these languages across the entire interface.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eComfyUI Image Generation Restored\u003c/strong\u003e: Fixed a critical bug where ComfyUI-based image generation was not functioning, ensuring users can once again effortlessly create and interact with AI-generated visuals in their workflows.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTool Server Loading and Visibility Restored\u003c/strong\u003e: Resolved an issue where connected tool servers were not loading or visible, restoring seamless integration and uninterrupted access to all external and custom tools directly within the platform.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis User Session Reliability\u003c/strong\u003e: Fixed a problem affecting the saving of user sessions in Redis, ensuring reliable login sessions, stable authentication, and secure multi-user environments.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eResolved Critical OIDC SSO Login Failure\u003c/strong\u003e: Fixed a critical issue where OIDC Single Sign-On (SSO) logins failed due to an error in setting the authentication token as a cookie during the redirect process. This ensures reliable and seamless authentication for users utilizing OIDC providers, restoring full login functionality that was impacted by previous security hardening.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePrevented UI Blocking by Unreachable Webhooks\u003c/strong\u003e: Resolved a critical performance and user experience issue where synchronous webhook calls to unreachable or slow endpoints would block the entire user interface for all users. Webhook requests are now processed asynchronously using \u0026quot;aiohttp\u0026quot;, ensuring that the UI remains responsive and functional even if webhook delivery encounters delays or failures.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/1db8dec4f52fc0fa8f8f7bfbb8ea5bde41fee17d\"\u003e\u003ccode\u003e1db8dec\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16821\"\u003e#16821\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/dafedf567561fdeb2f3010900cf99846820a3c69\"\u003e\u003ccode\u003edafedf5\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/37a3de0703c472db42633d6007a19a428c7e4e67\"\u003e\u003ccode\u003e37a3de0\u003c/code\u003e\u003c/a\u003e fix\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/72b25ab78bb00424e027d17427ec0c7fd78b4ed0\"\u003e\u003ccode\u003e72b25ab\u003c/code\u003e\u003c/a\u003e fix: image generation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/fbff4e19de591a440fcc5716e6796a6ed2d512b7\"\u003e\u003ccode\u003efbff4e1\u003c/code\u003e\u003c/a\u003e fix: reranking\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2777bab1485aad097aa41c44a76f49be141eb061\"\u003e\u003ccode\u003e2777bab\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16810\"\u003e#16810\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/4ec70e3d46ecf7b6453b0f93161203ff678fea3e\"\u003e\u003ccode\u003e4ec70e3\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/43b2eca4182df4d416665932b8320a18f9dbd09a\"\u003e\u003ccode\u003e43b2eca\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/99f7d1b62b2f1f8e862402495056b88baba88136\"\u003e\u003ccode\u003e99f7d1b\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/62a5db7719cfd2891e3cb5d4997b60c2e0f3c0eb\"\u003e\u003ccode\u003e62a5db7\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.22...v0.6.25\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.22\u0026new-version=0.6.25)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/6","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/6","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/6/packages"}},{"old_version":"0.6.22","new_version":"v0.6.23","update_type":"patch","path":null,"pr_created_at":"2025-08-22T08:12:11.000Z","version_change":"0.6.22 → v0.6.23","issue":{"uuid":"2765535190","node_id":"PR_kwDOPIpjyc6k1rfW","number":5,"state":"closed","title":"Bump open-webui/open-webui from 0.6.22 to v0.6.23","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-08-25T13:44:23.000Z","author_association":"NONE","state_reason":null,"created_at":"2025-08-22T08:12:11.000Z","updated_at":"2025-08-25T13:44:23.000Z","time_to_close":279132,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.22","new_version":"v0.6.23","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.22 to v0.6.23.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.23\u003c/h2\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eResolved Critical OIDC SSO Login Failure\u003c/strong\u003e: Fixed a critical issue where OIDC Single Sign-On (SSO) logins failed due to an error in setting the authentication token as a cookie during the redirect process. This ensures reliable and seamless authentication for users utilizing OIDC providers, restoring full login functionality that was impacted by previous security hardening.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePrevented UI Blocking by Unreachable Webhooks\u003c/strong\u003e: Resolved a critical performance and user experience issue where synchronous webhook calls to unreachable or slow endpoints would block the entire user interface for all users. Webhook requests are now processed asynchronously using \u0026quot;aiohttp\u0026quot;, ensuring that the UI remains responsive and functional even if webhook delivery encounters delays or failures.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003ePassword Change Option Hidden for Externally Authenticated Users\u003c/strong\u003e: Resolved an issue where the password change dialog was visible to users authenticated via external methods (e.g., LDAP, OIDC, Trusted Header). The option to change a password in user settings is now correctly hidden for these users, as their passwords are managed externally, streamlining the user interface and preventing confusion.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Temporary Chat and Permission Enforcement Issues\u003c/strong\u003e: Fixed a bug where temporary chats (identified by \u0026quot;chat_id = local\u0026quot;) incorrectly triggered database checks, leading to 404 errors. This also resolves the issue where the 'USER_PERMISSIONS_CHAT_TEMPORARY_ENFORCED' setting was not functioning as intended, ensuring temporary chat mode now works correctly for user roles.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eAdmin Model Visibility for Administrators\u003c/strong\u003e: Private models remained visible and usable for administrators in the chat model selector, even when the intended privacy setting (\u0026quot;ENABLE_ADMIN_WORKSPACE_CONTENT_ACCESS\u0026quot; - now renamed to \u0026quot;BYPASS_ADMIN_ACCESS_CONTROL\u0026quot;) was disabled. This ensures consistent enforcement of model access controls and adherence to the principle of least privilege.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eClarified Web Search Engine Label for DDGS\u003c/strong\u003e: Addressed user confusion and inaccurate labeling by renaming \u0026quot;duckduckgo\u0026quot; to \u0026quot;DDGS\u0026quot; (Dux Distributed Global Search) in the web search engine selector. This clarifies that the system utilizes DDGS, a metasearch library that aggregates results from various search providers, accurately reflecting its underlying functionality rather than implying exclusive use of DuckDuckGo's search engine.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Settings UI Reactivity and Visibility\u003c/strong\u003e: Resolved an issue where settings tabs for 'Connections' and 'Tools' did not dynamically update their visibility based on global administrative feature flags (e.g., 'enable_direct_connections'). The UI now reactively shows or hides these sections, ensuring a consistent and clear experience when administrators control feature availability.\u003c/li\u003e\n\u003cli\u003e🎚️ \u003cstrong\u003eRestored Model and Banner Reordering Functionality\u003c/strong\u003e: Fixed a bug that prevented administrators from reordering models in the Admin Panel's 'Models' settings and banners in the 'Interface' settings via drag-and-drop. The sortable functionality has been restored, allowing for proper customization of display order.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eRestored Custom Pending User Overlay Visibility\u003c/strong\u003e: Fixed an issue where the custom title and description configured for pending users were not visible. The application now correctly exposes these UI configuration settings to pending users, ensuring that the custom onboarding messages are displayed as intended.\u003c/li\u003e\n\u003cli\u003e📥 \u003cstrong\u003eFixed Community Function Import Compatibility\u003c/strong\u003e: Resolved an issue that prevented the successful import of function files downloaded from openwebui.com due to schema differences. The system now correctly processes these files, allowing for seamless integration of community-contributed functions.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eFixed Stale Ollama Version in Docker Images\u003c/strong\u003e: Resolved an issue where the Ollama installation within Docker images could become stale due to caching during the build process. The Dockerfile now includes a mechanism to invalidate the build cache for the Ollama installation step, ensuring that the latest version of Ollama is always installed.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eImproved Milvus Query Handling for Large Datasets\u003c/strong\u003e: Fixed a \u0026quot;MilvusException\u0026quot; that occurred when attempting to query more than 16384 entries from a Milvus collection. The query logic has been refactored to use \u0026quot;query_iterator()\u0026quot;, enabling efficient fetching of larger result sets in batches and resolving the previous limitation on the number of entries that could be retrieved.\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eRestored Message Toolbar Icons for Empty Messages with Files\u003c/strong\u003e: Fixed an issue where the edit, copy, and delete icons were not displayed on user messages that contained an attached file but no text content. This ensures full interaction capabilities for all message types, allowing users to manage their messages consistently.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Streaming Interruption for Kimi-Dev Models\u003c/strong\u003e: Fixed an issue where streaming responses from Kimi-Dev models would halt prematurely upon encountering specific 'thinking' tokens (◁think▷, ◁/think▷). The system now correctly processes these tokens, ensuring uninterrupted streaming and proper handling of hidden or collapsible thinking sections.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eEnhanced Knowledge Base Search Functionality\u003c/strong\u003e: Improved the search capability within the 'Knowledge' section of the Workspace. Previously, searching for knowledge bases required exact term matches or starting with the first letter. Now, the search algorithm has been refined to allow broader, less exact matches, making it easier and more intuitive to find relevant knowledge bases.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eResolved Chinese Input 'Enter' Key Issue (macOS \u0026amp; iOS Safari)\u003c/strong\u003e: Fixed a bug where pressing the 'Enter' key during text composition with Input Method Editors (IMEs) on macOS and iOS Safari browsers would prematurely send the message. The system now robustly handles the composition state by addressing a 'compositionend' event bug specific to Safari, ensuring a smooth and expected typing experience for users of various languages, including Chinese and Korean.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eResolved OAUTH_GROUPS_CLAIM Configuration Issue\u003c/strong\u003e: Fixed a bug where the \u0026quot;OAUTH_GROUPS_CLAIM\u0026quot; environment variable was not correctly parsed due to a typo in the configuration file. This ensures that OAuth group management features, including automatic group creation, now correctly utilize the specified claim from the identity provider, allowing for seamless integration with external user directories like Keycloak.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eResolved Azure PostgreSQL pgvector Extension Permissions\u003c/strong\u003e: Fixed an issue preventing the creation of \u0026quot;pgvector\u0026quot; and \u0026quot;pgcrypto\u0026quot; extensions on Azure PostgreSQL Flexible Servers due to permission limitations (e.g., 'Only members of \u0026quot;azure_pg_admin\u0026quot; are allowed to use \u0026quot;CREATE EXTENSION\u0026quot;'). The extension creation process now includes a conditional check, ensuring seamless deployment and compatibility with Azure PostgreSQL environments even with restricted database user permissions.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Backend Path Resolution and Alembic Stability\u003c/strong\u003e: Fixed issues causing Alembic database migrations to fail due to incorrect path resolution within the application. By implementing canonical path resolution for core directories and refining Alembic configuration, the robustness and correctness of internal pathing have been significantly enhanced, ensuring reliable database operations.\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eResolved Arena Model Identification in Feedback History\u003c/strong\u003e: Fixed an issue where the model used for feedback in arena settings was incorrectly reported as 'arena-model' in the evaluation history. The system now correctly logs and displays the actual model ID that received the feedback, restoring clarity and enabling proper analysis of model performance in arena environments.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eResolved Icon Overlap in 'Her' Theme\u003c/strong\u003e: Fixed a visual glitch in the 'Her' theme where icons would overlap on the loading screen and certain icons appeared incongruous. The display has been corrected to ensure proper visual presentation and theme consistency.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.23] - 2025-08-21\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eAsynchronous Chat Payload Processing\u003c/strong\u003e: Refactored the chat completion pipeline to return a response immediately for streaming requests involving web search or tool calls. This enables users to stop ongoing generations promptly and preventing network timeouts during lengthy preprocessing phases, thus significantly improving user experience and responsiveness.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eAsynchronous File Upload with Polling\u003c/strong\u003e: Implemented an asynchronous file upload process with frontend polling to resolve gateway timeouts and improve reliability when uploading large files. This ensures that even lengthy file processing, such as embedding or transcription, does not block the user interface or lead to connection timeouts, providing a smoother experience for all file operations.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eDatabase Performance Indexes and Migration Script\u003c/strong\u003e: Introduced new database indexes on the \u0026quot;chat\u0026quot;, \u0026quot;tag\u0026quot;, and \u0026quot;function\u0026quot; tables to significantly enhance query performance for SQLite and PostgreSQL installations. For existing deployments, a new Alembic migration script is included to seamlessly apply these indexes, ensuring faster filtering and sorting operations across the platform.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eEnhanced Database Performance Options\u003c/strong\u003e: Introduced new configurable options to significantly improve database performance, especially for SQLite. This includes \u0026quot;DATABASE_ENABLE_SQLITE_WAL\u0026quot; to enable SQLite WAL (Write-Ahead Logging) mode for concurrent operations, and \u0026quot;DATABASE_DEDUPLICATE_INTERVAL\u0026quot; which, in conjunction with a new deduplication mechanism, reduces redundant updates to \u0026quot;user.last_active_at\u0026quot;, minimizing write conflicts across all database types.\u003c/li\u003e\n\u003cli\u003e💾 \u003cstrong\u003eSave Temporary Chats Button\u003c/strong\u003e: Introduced a new 'Save Chat' button for conversations initiated in temporary mode. This allows users to permanently save valuable temporary conversations to their chat history, providing greater flexibility and ensuring important discussions are not lost.\u003c/li\u003e\n\u003cli\u003e📂 \u003cstrong\u003eChat Movement Options in Menu\u003c/strong\u003e: Added the ability to move chats directly to folders from the chat menu. This enhances chat organization and allows users to manage their conversations more efficiently by relocating them between folders with ease.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eLanguage-Aware Follow-Up Suggestions\u003c/strong\u003e: Enhanced the AI's follow-up question generation to dynamically adapt to the primary language of the current chat. Follow-up prompts will now be suggested in the same language the user and AI are conversing in, ensuring more natural and contextually relevant interactions.\u003c/li\u003e\n\u003cli\u003e👤 \u003cstrong\u003eExpanded User Profile Details\u003c/strong\u003e: Introduced new user profile fields including username, bio, gender, and date of birth, allowing for more comprehensive user customization and information management. This enhancement includes corresponding updates to the database schema, API, and user interface for seamless integration.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eDirect Navigation to User Groups from User Edit\u003c/strong\u003e: Enhanced the user edit modal to include a direct link to the associated user group. This allows administrators to quickly navigate from a user's profile to their group settings, streamlining user and group management workflows.\u003c/li\u003e\n\u003cli\u003e🔧 \u003cstrong\u003eEnhanced External Tool Server Compatibility\u003c/strong\u003e: Improved handling of responses from external tool servers, allowing both the backend and frontend to process plain text content in addition to JSON, ensuring greater flexibility and integration with diverse tool outputs.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eEnhanced Audio Transcription Language Fallback and Deepgram Support\u003c/strong\u003e: Implemented a robust language fallback mechanism for both OpenAI and Deepgram Speech-to-Text (STT) API calls. If a specified language parameter is not supported by the model or provider, the system will now intelligently retry the transcription without the language parameter or with a default, ensuring greater reliability and preventing failed API calls. This also specifically adds and refines support for the audio language parameter in Deepgram API integrations.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eOptimized Hybrid Search Performance for BM25 Weight Configuration\u003c/strong\u003e: Enhanced hybrid search to significantly improve performance when the BM25 weight is set to 0 or less. This optimization intelligently disables unnecessary collection retrieval and BM25 ranking calculations, leading to faster search results without impacting accuracy for configurations that do not utilize lexical search contributions.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConfigurable Code Interpreter Module Blacklist\u003c/strong\u003e: Introduced the \u0026quot;CODE_INTERPRETER_BLACKLISTED_MODULES\u0026quot; environment variable, allowing administrators to specify Python modules that are forbidden from being imported or executed within the code interpreter. This significantly enhances the security posture by mitigating risks associated with arbitrary code execution, such as unauthorized data access, system manipulation, or outbound connections.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eEnhanced OAuth Role Claim Handling\u003c/strong\u003e: Improved compatibility with diverse OAuth providers by allowing role claims to be supplied as single strings or integers, in addition to arrays. The system now automatically normalizes these single-value claims into arrays for consistent processing, streamlining integration with identity providers that format role data differently.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eConfigurable Tool Call Timeout\u003c/strong\u003e: Introduced the \u0026quot;AIOHTTP_CLIENT_TIMEOUT\u0026quot; environment variable, allowing administrators to specify custom timeout durations for external tool calls, which is crucial for integrations with tools that have varying or extended response times.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Tool Callable Generation for Google genai SDK\u003c/strong\u003e: Enhanced the creation of tool callables to directly support native function calling within the Google 'genai' SDK. This refactoring ensures proper signature inference and removes extraneous parameters, enabling seamless integration for advanced AI workflows using Google's generative AI models.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eDynamic Loading of 'kokoro-js'\u003c/strong\u003e: Implemented dynamic loading for the 'kokoro-js' library, preventing failures and improving compatibility on older iOS browsers that may not support direct imports or certain modern JavaScript APIs like 'DecompressionStream'.\u003c/li\u003e\n\u003cli\u003e🖥️ \u003cstrong\u003eImproved Command List Visibility on Small Screens\u003c/strong\u003e: Resolved an issue where the top items in command lists (e.g., Knowledge Base, Models, Prompts) were hidden or overlapped by the header on smaller screen sizes or specific browser zoom levels. The command option lists now dynamically adjust their height, ensuring all items are fully visible and accessible with proper scrolling.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eImproved Docker Image Compatibility for Arbitrary UIDs\u003c/strong\u003e: Fixed issues preventing the Open WebUI container from running in environments with arbitrary User IDs (UIDs), such as OpenShift's restricted Security Context Constraints (SCC). The Dockerfile has been updated to correctly set file system permissions for \u0026quot;/app\u0026quot; and \u0026quot;/root\u0026quot; directories, ensuring they are writable by processes running with a supplemental GID 0, thus resolving permission errors for Python libraries and application caches.\u003c/li\u003e\n\u003cli\u003e♿ \u003cstrong\u003eAccessibility Enhancements\u003c/strong\u003e: Significantly improved the semantic structure of chat messages by using \u0026quot;section\u0026quot;, \u0026quot;h2\u0026quot;, \u0026quot;ul\u0026quot;, and \u0026quot;li\u0026quot; HTML tags, and enhanced screen reader compatibility by explicitly hiding decorative images with \u0026quot;aria-hidden\u0026quot; attributes. This refactoring provides clearer structural context and improves overall accessibility and web standards compliance for the conversation flow.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Significantly expanded internationalization support throughout the user interface, translating numerous user-facing strings in toast messages, placeholders, and other UI elements. This, alongside continuous refinement and expansion of translations for languages including Brazilian Portuguese, Kabyle (Taqbaylit), Czech, Finnish, Chinese (Simplified), Chinese (Traditional), and German, and general fixes for several other translation files, further enhances linguistic coverage and user experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eResolved Critical OIDC SSO Login Failure\u003c/strong\u003e: Fixed a critical issue where OIDC Single Sign-On (SSO) logins failed due to an error in setting the authentication token as a cookie during the redirect process. This ensures reliable and seamless authentication for users utilizing OIDC providers, restoring full login functionality that was impacted by previous security hardening.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePrevented UI Blocking by Unreachable Webhooks\u003c/strong\u003e: Resolved a critical performance and user experience issue where synchronous webhook calls to unreachable or slow endpoints would block the entire user interface for all users. Webhook requests are now processed asynchronously using \u0026quot;aiohttp\u0026quot;, ensuring that the UI remains responsive and functional even if webhook delivery encounters delays or failures.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003ePassword Change Option Hidden for Externally Authenticated Users\u003c/strong\u003e: Resolved an issue where the password change dialog was visible to users authenticated via external methods (e.g., LDAP, OIDC, Trusted Header). The option to change a password in user settings is now correctly hidden for these users, as their passwords are managed externally, streamlining the user interface and preventing confusion.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Temporary Chat and Permission Enforcement Issues\u003c/strong\u003e: Fixed a bug where temporary chats (identified by \u0026quot;chat_id = local\u0026quot;) incorrectly triggered database checks, leading to 404 errors. This also resolves the issue where the 'USER_PERMISSIONS_CHAT_TEMPORARY_ENFORCED' setting was not functioning as intended, ensuring temporary chat mode now works correctly for user roles.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eAdmin Model Visibility for Administrators\u003c/strong\u003e: Private models remained visible and usable for administrators in the chat model selector, even when the intended privacy setting (\u0026quot;ENABLE_ADMIN_WORKSPACE_CONTENT_ACCESS\u0026quot; - now renamed to \u0026quot;BYPASS_ADMIN_ACCESS_CONTROL\u0026quot;) was disabled. This ensures consistent enforcement of model access controls and adherence to the principle of least privilege.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eClarified Web Search Engine Label for DDGS\u003c/strong\u003e: Addressed user confusion and inaccurate labeling by renaming \u0026quot;duckduckgo\u0026quot; to \u0026quot;DDGS\u0026quot; (Dux Distributed Global Search) in the web search engine selector. This clarifies that the system utilizes DDGS, a metasearch library that aggregates results from various search providers, accurately reflecting its underlying functionality rather than implying exclusive use of DuckDuckGo's search engine.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Settings UI Reactivity and Visibility\u003c/strong\u003e: Resolved an issue where settings tabs for 'Connections' and 'Tools' did not dynamically update their visibility based on global administrative feature flags (e.g., 'enable_direct_connections'). The UI now reactively shows or hides these sections, ensuring a consistent and clear experience when administrators control feature availability.\u003c/li\u003e\n\u003cli\u003e🎚️ \u003cstrong\u003eRestored Model and Banner Reordering Functionality\u003c/strong\u003e: Fixed a bug that prevented administrators from reordering models in the Admin Panel's 'Models' settings and banners in the 'Interface' settings via drag-and-drop. The sortable functionality has been restored, allowing for proper customization of display order.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eRestored Custom Pending User Overlay Visibility\u003c/strong\u003e: Fixed an issue where the custom title and description configured for pending users were not visible. The application now correctly exposes these UI configuration settings to pending users, ensuring that the custom onboarding messages are displayed as intended.\u003c/li\u003e\n\u003cli\u003e📥 \u003cstrong\u003eFixed Community Function Import Compatibility\u003c/strong\u003e: Resolved an issue that prevented the successful import of function files downloaded from openwebui.com due to schema differences. The system now correctly processes these files, allowing for seamless integration of community-contributed functions.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eFixed Stale Ollama Version in Docker Images\u003c/strong\u003e: Resolved an issue where the Ollama installation within Docker images could become stale due to caching during the build process. The Dockerfile now includes a mechanism to invalidate the build cache for the Ollama installation step, ensuring that the latest version of Ollama is always installed.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eImproved Milvus Query Handling for Large Datasets\u003c/strong\u003e: Fixed a \u0026quot;MilvusException\u0026quot; that occurred when attempting to query more than 16384 entries from a Milvus collection. The query logic has been refactored to use \u0026quot;query_iterator()\u0026quot;, enabling efficient fetching of larger result sets in batches and resolving the previous limitation on the number of entries that could be retrieved.\u003c/li\u003e\n\u003cli\u003e🐛 \u003cstrong\u003eRestored Message Toolbar Icons for Empty Messages with Files\u003c/strong\u003e: Fixed an issue where the edit, copy, and delete icons were not displayed on user messages that contained an attached file but no text content. This ensures full interaction capabilities for all message types, allowing users to manage their messages consistently.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003eResolved Streaming Interruption for Kimi-Dev Models\u003c/strong\u003e: Fixed an issue where streaming responses from Kimi-Dev models would halt prematurely upon encountering specific 'thinking' tokens (◁think▷, ◁/think▷). The system now correctly processes these tokens, ensuring uninterrupted streaming and proper handling of hidden or collapsible thinking sections.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003eEnhanced Knowledge Base Search Functionality\u003c/strong\u003e: Improved the search capability within the 'Knowledge' section of the Workspace. Previously, searching for knowledge bases required exact term matches or starting with the first letter. Now, the search algorithm has been refined to allow broader, less exact matches, making it easier and more intuitive to find relevant knowledge bases.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eResolved Chinese Input 'Enter' Key Issue (macOS \u0026amp; iOS Safari)\u003c/strong\u003e: Fixed a bug where pressing the 'Enter' key during text composition with Input Method Editors (IMEs) on macOS and iOS Safari browsers would prematurely send the message. The system now robustly handles the composition state by addressing a 'compositionend' event bug specific to Safari, ensuring a smooth and expected typing experience for users of various languages, including Chinese and Korean.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eResolved OAUTH_GROUPS_CLAIM Configuration Issue\u003c/strong\u003e: Fixed a bug where the \u0026quot;OAUTH_GROUPS_CLAIM\u0026quot; environment variable was not correctly parsed due to a typo in the configuration file. This ensures that OAuth group management features, including automatic group creation, now correctly utilize the specified claim from the identity provider, allowing for seamless integration with external user directories like Keycloak.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eResolved Azure PostgreSQL pgvector Extension Permissions\u003c/strong\u003e: Fixed an issue preventing the creation of \u0026quot;pgvector\u0026quot; and \u0026quot;pgcrypto\u0026quot; extensions on Azure PostgreSQL Flexible Servers due to permission limitations (e.g., 'Only members of \u0026quot;azure_pg_admin\u0026quot; are allowed to use \u0026quot;CREATE EXTENSION\u0026quot;'). The extension creation process now includes a conditional check, ensuring seamless deployment and compatibility with Azure PostgreSQL environments even with restricted database user permissions.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eImproved Backend Path Resolution and Alembic Stability\u003c/strong\u003e: Fixed issues causing Alembic database migrations to fail due to incorrect path resolution within the application. By implementing canonical path resolution for core directories and refining Alembic configuration, the robustness and correctness of internal pathing have been significantly enhanced, ensuring reliable database operations.\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eResolved Arena Model Identification in Feedback History\u003c/strong\u003e: Fixed an issue where the model used for feedback in arena settings was incorrectly reported as 'arena-model' in the evaluation history. The system now correctly logs and displays the actual model ID that received the feedback, restoring clarity and enabling proper analysis of model performance in arena environments.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eResolved Icon Overlap in 'Her' Theme\u003c/strong\u003e: Fixed a visual glitch in the 'Her' theme where icons would overlap on the loading screen and certain icons appeared incongruous. The display has been corrected to ensure proper visual presentation and theme consistency.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eResolved Model Sorting TypeError with Null Names\u003c/strong\u003e: Fixed a \u0026quot;TypeError\u0026quot; that occurred in the \u0026quot;/api/models\u0026quot; endpoint when sorting models with null or missing names. The model sorting logic has been improved to gracefully handle such edge cases by ensuring that model IDs and names are treated as empty strings if their values are null or undefined, preventing comparison errors and improving API stability.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/407dc9a401fc2382df06d776dbd8ba95dffda38a\"\u003e\u003ccode\u003e407dc9a\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16507\"\u003e#16507\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9fb2c9c86d0dfb1416198befea37715d1be0eb06\"\u003e\u003ccode\u003e9fb2c9c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/60b8cfb9fa2228eac878c3c52eccdff7abc4d384\"\u003e\u003ccode\u003e60b8cfb\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5a66f69460381a81dfd8e98824b094557befbe8b\"\u003e\u003ccode\u003e5a66f69\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16779\"\u003e#16779\u003c/a\u003e from mahenning/fix--clean-unload-embed/reranker-models\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/578f116ebb95b03f0205f93b1fd66f71e92bb6e5\"\u003e\u003ccode\u003e578f116\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d3b5ba8472218cf1067475aafeb4c860f7998a19\"\u003e\u003ccode\u003ed3b5ba8\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16767\"\u003e#16767\u003c/a\u003e from Classic298/patch-2\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/3e28c46026687414290d13255f4d19fa7a1aecd9\"\u003e\u003ccode\u003e3e28c46\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/71d7ba6c07ce858ed9886928d398e66fa39cb6af\"\u003e\u003ccode\u003e71d7ba6\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16785\"\u003e#16785\u003c/a\u003e from ShirasawaSama/i18n/improve-chinese-translation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/581c0f137e5afcd56083071e01ac0ff26e5c82b1\"\u003e\u003ccode\u003e581c0f1\u003c/code\u003e\u003c/a\u003e i18n: improve chinese translation\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f2e78d79407004dfe5bc40a6ef3e71bf4088d273\"\u003e\u003ccode\u003ef2e78d7\u003c/code\u003e\u003c/a\u003e More formatting\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.22...v0.6.23\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.22\u0026new-version=v0.6.23)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/5","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/5","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/5/packages"}},{"old_version":"0.6.21","new_version":"v0.6.22","update_type":"patch","path":null,"pr_created_at":"2025-08-12T13:44:36.000Z","version_change":"0.6.21 → v0.6.22","issue":{"uuid":"3314343338","node_id":"PR_kwDOPIpjyc6jRcl5","number":1,"state":"closed","title":"Bump open-webui/open-webui from 0.6.21 to v0.6.22","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-08-13T01:29:26.000Z","author_association":"NONE","state_reason":null,"created_at":"2025-08-12T13:44:36.000Z","updated_at":"2025-08-13T01:29:27.000Z","time_to_close":42290,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"0.6.21","new_version":"v0.6.22","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from 0.6.21 to v0.6.22.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.22\u003c/h2\u003e\n\u003ch2\u003e[0.6.22] - 2025-08-11\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eOpenAI API '/v1' Endpoint Compatibility\u003c/strong\u003e: Enhanced API compatibility by supporting requests to paths like '/v1/models', '/v1/embeddings', and '/v1/chat/completions'. This allows Open WebUI to integrate more seamlessly with tools that expect OpenAI's '/v1' API structure.\u003c/li\u003e\n\u003cli\u003e🪄 \u003cstrong\u003eToggle for Guided Response Regeneration Menu\u003c/strong\u003e: Introduced a new setting in 'Interface' settings, providing the ability to enable or disable the expanded guided response regeneration menu. This offers users more control over their chat workflow and interface preferences.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eGeneral UI/UX Enhancements\u003c/strong\u003e: Implemented various user interface and experience improvements, including more rounded corners for cards in the Knowledge, Prompts, and Tools sections, and minor layout adjustments within the chat Navbar for improved visual consistency.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Introduced support for the Kabyle (Taqbaylit) language, refined and expanded translations for Chinese, expanding the platform's linguistic coverage.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🐞 \u003cstrong\u003eOpenAI Error Message Propagation\u003c/strong\u003e: Resolved an issue where specific OpenAI API errors (e.g., 'Organization Not Verified') were obscured by generic 'JSONResponse' iterable errors. The system now correctly propagates detailed and actionable error messages from OpenAI to the user.\u003c/li\u003e\n\u003cli\u003e🌲 \u003cstrong\u003ePinecone Insert Issue\u003c/strong\u003e: Fixed a bug that prevented proper insertion of items into Pinecone vector databases.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eS3 Vector Issue\u003c/strong\u003e: Resolved a bug where s3vector functionality failed due to incorrect import paths.\u003c/li\u003e\n\u003cli\u003e🏠 \u003cstrong\u003eLanding Page Option Setting Not Working\u003c/strong\u003e: Fixed an issue where the landing page option in settings was not functioning as intended.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/blockquote\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.22] - 2025-08-11\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eOpenAI API '/v1' Endpoint Compatibility\u003c/strong\u003e: Enhanced API compatibility by supporting requests to paths like '/v1/models', '/v1/embeddings', and '/v1/chat/completions'. This allows Open WebUI to integrate more seamlessly with tools that expect OpenAI's '/v1' API structure.\u003c/li\u003e\n\u003cli\u003e🪄 \u003cstrong\u003eToggle for Guided Response Regeneration Menu\u003c/strong\u003e: Introduced a new setting in 'Interface' settings, providing the ability to enable or disable the expanded guided response regeneration menu. This offers users more control over their chat workflow and interface preferences.\u003c/li\u003e\n\u003cli\u003e✨ \u003cstrong\u003eGeneral UI/UX Enhancements\u003c/strong\u003e: Implemented various user interface and experience improvements, including more rounded corners for cards in the Knowledge, Prompts, and Tools sections, and minor layout adjustments within the chat Navbar for improved visual consistency.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Introduced support for the Kabyle (Taqbaylit) language, refined and expanded translations for Chinese, expanding the platform's linguistic coverage.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🐞 \u003cstrong\u003eOpenAI Error Message Propagation\u003c/strong\u003e: Resolved an issue where specific OpenAI API errors (e.g., 'Organization Not Verified') were obscured by generic 'JSONResponse' iterable errors. The system now correctly propagates detailed and actionable error messages from OpenAI to the user.\u003c/li\u003e\n\u003cli\u003e🌲 \u003cstrong\u003ePinecone Insert Issue\u003c/strong\u003e: Fixed a bug that prevented proper insertion of items into Pinecone vector databases.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eS3 Vector Issue\u003c/strong\u003e: Resolved a bug where s3vector functionality failed due to incorrect import paths.\u003c/li\u003e\n\u003cli\u003e🏠 \u003cstrong\u003eLanding Page Option Setting Not Working\u003c/strong\u003e: Fixed an issue where the landing page option in settings was not functioning as intended.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/blockquote\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/438e5d966f0f64f9ea3feab22724a5bd96a4127b\"\u003e\u003ccode\u003e438e5d9\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16456\"\u003e#16456\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/17cc3b7d729dbb2e1f274b7c038b6bd55318db19\"\u003e\u003ccode\u003e17cc3b7\u003c/code\u003e\u003c/a\u003e fix: chat item generate title button\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d89c5b6c30cb85f7c84f4a18aa25a856464110bb\"\u003e\u003ccode\u003ed89c5b6\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8fd5006b6fe8536275af6f17e420ad4a669374d0\"\u003e\u003ccode\u003e8fd5006\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/97448e25eceea278406e56b578fa24cec949661f\"\u003e\u003ccode\u003e97448e2\u003c/code\u003e\u003c/a\u003e fix: openai error handling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8916a284bd729e538a185f73567cb272b85aef76\"\u003e\u003ccode\u003e8916a28\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/8e2aaaf94f39983b2b1efe8b468f5e7b4887ca37\"\u003e\u003ccode\u003e8e2aaaf\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e15f8b8bafa66babd3eb44dcc4d834ff6f8c44f4\"\u003e\u003ccode\u003ee15f8b8\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/16458\"\u003e#16458\u003c/a\u003e from Classic298/patch-3\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/890691319f4af2e8db5ef49b0a6dc825607e080b\"\u003e\u003ccode\u003e8906913\u003c/code\u003e\u003c/a\u003e fix: s3vector import issue\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/21094ca88b4ae806d33d0759904c9dc9f08f1dee\"\u003e\u003ccode\u003e21094ca\u003c/code\u003e\u003c/a\u003e fix: pinecone insert issue\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.6.21...v0.6.22\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=0.6.21\u0026new-version=v0.6.22)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/rahulsalvi/open-webui/pull/1","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/rahulsalvi%2Fopen-webui/issues/1","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/1/packages"}},{"old_version":"v0.5.20","new_version":"0.6.18","update_type":"minor","path":"/docker","pr_created_at":"2025-07-21T22:55:02.000Z","version_change":"v0.5.20 → 0.6.18","issue":{"uuid":"2683380391","node_id":"PR_kwDOM-FVBM6f8SKn","number":76,"state":"open","title":"Bump open-webui/open-webui from v0.5.20 to 0.6.18 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-07-21T22:55:02.000Z","updated_at":"2025-07-21T22:55:03.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"0.6.18","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to 0.6.18.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.18\u003c/h2\u003e\n\u003ch2\u003e[0.6.18] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚑 \u003cstrong\u003eUsers Not Loading in Groups\u003c/strong\u003e: Resolved an issue where user list was not displaying within user groups, restoring full visibility and management of group memberships for teams and admins.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.17\u003c/h2\u003e\n\u003ch2\u003e[0.6.17] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📂 \u003cstrong\u003eDedicated Folder View with Chat List\u003c/strong\u003e: Clicking a folder now reveals a brand-new landing page showcasing a list of all chats within that folder, making navigation simpler and giving teams immediate visibility into project-specific conversations.\u003c/li\u003e\n\u003cli\u003e🆕 \u003cstrong\u003eStreamlined Folder Creation Modal\u003c/strong\u003e: Creating a new folder is now a seamless, unified experience with a dedicated modal that visually and functionally matches the edit folder flow, making workspace organization more intuitive and error-free for all users.\u003c/li\u003e\n\u003cli\u003e🗃️ \u003cstrong\u003eDirect File Uploads to Folder Knowledge\u003c/strong\u003e: You can now upload files straight to a folder’s knowledge—empowering you to enrich project spaces by adding resources and documents directly, without the need to pre-create knowledge bases beforehand.\u003c/li\u003e\n\u003cli\u003e🔎 \u003cstrong\u003eChat Preview in Search\u003c/strong\u003e: When searching chats, instantly preview results in context without having to open them—making discovery, auditing, and recall dramatically quicker, especially in large, active teams.\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Upload and Inline Insertion in Notes\u003c/strong\u003e: Notes now support inserting images directly among your text, letting you create rich, visually structured documentation, brainstorms, or reports in a more natural and engaging way—no more images just as attachments.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eEnhanced Note Selection Editing and Q\u0026amp;A\u003c/strong\u003e: Select any portion of your notes to either edit just the highlighted part or ask focused questions about that content—streamlining workflows, boosting productivity, and making reviews or AI-powered enhancements more targeted.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCopy Notes as Rich Text\u003c/strong\u003e: Copy entire notes—including all formatting, images, and structure—directly as rich text for seamless pasting into emails, reports, or other tools, maintaining clarity and consistency outside the WebUI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFade-In Streaming Text Experience\u003c/strong\u003e: Live-generated responses now elegantly fade in as the AI streams them, creating a more natural and visually engaging reading experience; easily toggled off in Interface settings if you prefer static displays.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSettings for Follow-Up Prompts\u003c/strong\u003e: Fine-tune your follow-up prompt experience—with new controls, you can choose to keep them visible or have them inserted directly into the message input instead of auto-submitting, giving you more flexibility and control over your workflow.\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003ePrompt Variable Documentation Quick Link\u003c/strong\u003e: Access documentation for prompt variables in one click from the prompt editor modal—shortening the learning curve and making advanced prompt-building more accessible.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eActive and Total User Metrics for Telemetry\u003c/strong\u003e: Gain valuable insights into usage patterns and platform engagement with new metrics tracking active and total users—enhancing auditability and planning for large organizations.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eTraceability with Log Trace and Span IDs\u003c/strong\u003e: Each log entry now carries detailed trace and span IDs, making it much easier for admins to pinpoint and resolve issues across distributed systems or in complex troubleshooting.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eUser Group Add/Remove Endpoints\u003c/strong\u003e: Effortlessly add or remove users from groups with new, improved endpoints—giving admins and team leads faster, clearer control over collaboration and permissions.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eNote Settings and Controls Streamlined\u003c/strong\u003e: The main “Settings” for notes are now simply called “Controls”, and note files now reside in a dedicated controls section, decluttering navigation and making it easier to find and configure note-related options.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eFaster Admin User Page Loads\u003c/strong\u003e: The user list endpoint for admins has been optimized to exclude heavy profile images, speeding up load times for large teams and reducing waiting during administrative tasks.\u003c/li\u003e\n\u003cli\u003e📡 \u003cstrong\u003eChat ID Header Forwarding\u003c/strong\u003e: Ollama and OpenAI router requests now include the chat ID in request headers, enabling better request correlation and debugging capabilities across AI model integrations.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEnhanced Reasoning Tag Processing\u003c/strong\u003e: Improved and expanded reasoning tag parsing to handle various tag formats more robustly, including standard XML-style tags and custom delimiters, ensuring better AI reasoning transparency and debugging capabilities.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth Token Endpoint Authentication Method\u003c/strong\u003e: Added configurable OAuth token endpoint authentication method support, providing enhanced flexibility and security options for enterprise OAuth integrations and identity provider compatibility.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis Sentinel High Availability Support\u003c/strong\u003e: Comprehensive Redis Sentinel failover implementation with automatic master discovery, intelligent retry logic for connection failures, and seamless operation during master node outages—eliminating single points of failure and ensuring continuous service availability in production deployments.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Refined and expanded translations for Simplified Chinese, Traditional Chinese, French, German, Korean, and Polish, ensuring a more fluent and native experience for global users across all supported languages.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eHybrid Search Functionality Restored\u003c/strong\u003e: Hybrid search now works seamlessly again—enabling more accurate, relevant, and comprehensive knowledge discovery across all RAG-powered workflows.\u003c/li\u003e\n\u003cli\u003e🚦 \u003cstrong\u003eNote Chat - Edit Button Disabled During AI Generation\u003c/strong\u003e: The edit button when chatting with a note is now disabled while the AI is responding—preventing accidental edits and ensuring workflow clarity during chat sessions.\u003c/li\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eCleaner Database Credentials\u003c/strong\u003e: Database connection no longer duplicates ‘@’ in credentials, preventing potential connection issues and ensuring smoother, more reliable integrations.\u003c/li\u003e\n\u003cli\u003e🧑‍💻 \u003cstrong\u003eFile Deletion Now Removes Related Vector Data\u003c/strong\u003e: When files are deleted from storage, they are now purged from the vector database as well, ensuring clean data management and preventing clutter or stale search results.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eFiles Modal Translation Issues Fixed\u003c/strong\u003e: All modal dialog strings—including “Using Entire Document” and “Using Focused Retrieval”—are now fully translated for a more consistent and localized UI experience.\u003c/li\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eDrag-and-Drop File Upload Disabled for Unsupported Models\u003c/strong\u003e: File upload by drag-and-drop is disabled when using models that do not support attachments—removing confusion and preventing workflow interruptions.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eOllama Tool Calls Now Reliable\u003c/strong\u003e: Fixed issues with Ollama-based tool calls, ensuring uninterrupted AI augmentation and tool use for every chat.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eMIME Type Help String Correction\u003c/strong\u003e: Cleaned up mimetype help text by removing extraneous characters, providing clearer guidance for file upload configurations.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eNote Editor Permission Fix\u003c/strong\u003e: Removed unnecessary admin-only restriction from note chat functionality, allowing all authorized users to access note editing features as intended.\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eChat Sources Handling Improved\u003c/strong\u003e: Fixed sources handling logic to prevent duplicate source assignments in chat messages, ensuring cleaner and more accurate source attribution during conversations.\u003c/li\u003e\n\u003cli\u003e😀 \u003cstrong\u003eEmoji Generation Error Handling\u003c/strong\u003e: Improved error handling in audio router and fixed metadata structure for emoji generation tasks, preventing crashes and ensuring more reliable emoji generation functionality.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eFolder System Prompt Permission Enforcement\u003c/strong\u003e: System prompt fields in folder edit modal are now properly hidden for users without system prompt permissions, ensuring consistent security policy enforcement across all folder management interfaces.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eWebSocket Redis Lock Timeout Type Conversion\u003c/strong\u003e: Fixed proper integer type conversion for WebSocket Redis lock timeout configuration with robust error handling, preventing potential configuration errors and ensuring stable WebSocket connections.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003ePostHog Dependency Added\u003c/strong\u003e: Added PostHog 5.4.0 library to resolve ChromaDB compatibility issues, ensuring stable vector database operations and preventing library version conflicts during deployment.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.18] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🚑 \u003cstrong\u003eUsers Not Loading in Groups\u003c/strong\u003e: Resolved an issue where user list was not displaying within user groups, restoring full visibility and management of group memberships for teams and admins.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.17] - 2025-07-19\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e📂 \u003cstrong\u003eDedicated Folder View with Chat List\u003c/strong\u003e: Clicking a folder now reveals a brand-new landing page showcasing a list of all chats within that folder, making navigation simpler and giving teams immediate visibility into project-specific conversations.\u003c/li\u003e\n\u003cli\u003e🆕 \u003cstrong\u003eStreamlined Folder Creation Modal\u003c/strong\u003e: Creating a new folder is now a seamless, unified experience with a dedicated modal that visually and functionally matches the edit folder flow, making workspace organization more intuitive and error-free for all users.\u003c/li\u003e\n\u003cli\u003e🗃️ \u003cstrong\u003eDirect File Uploads to Folder Knowledge\u003c/strong\u003e: You can now upload files straight to a folder’s knowledge—empowering you to enrich project spaces by adding resources and documents directly, without the need to pre-create knowledge bases beforehand.\u003c/li\u003e\n\u003cli\u003e🔎 \u003cstrong\u003eChat Preview in Search\u003c/strong\u003e: When searching chats, instantly preview results in context without having to open them—making discovery, auditing, and recall dramatically quicker, especially in large, active teams.\u003c/li\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eImage Upload and Inline Insertion in Notes\u003c/strong\u003e: Notes now support inserting images directly among your text, letting you create rich, visually structured documentation, brainstorms, or reports in a more natural and engaging way—no more images just as attachments.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eEnhanced Note Selection Editing and Q\u0026amp;A\u003c/strong\u003e: Select any portion of your notes to either edit just the highlighted part or ask focused questions about that content—streamlining workflows, boosting productivity, and making reviews or AI-powered enhancements more targeted.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCopy Notes as Rich Text\u003c/strong\u003e: Copy entire notes—including all formatting, images, and structure—directly as rich text for seamless pasting into emails, reports, or other tools, maintaining clarity and consistency outside the WebUI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eFade-In Streaming Text Experience\u003c/strong\u003e: Live-generated responses now elegantly fade in as the AI streams them, creating a more natural and visually engaging reading experience; easily toggled off in Interface settings if you prefer static displays.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSettings for Follow-Up Prompts\u003c/strong\u003e: Fine-tune your follow-up prompt experience—with new controls, you can choose to keep them visible or have them inserted directly into the message input instead of auto-submitting, giving you more flexibility and control over your workflow.\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003ePrompt Variable Documentation Quick Link\u003c/strong\u003e: Access documentation for prompt variables in one click from the prompt editor modal—shortening the learning curve and making advanced prompt-building more accessible.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eActive and Total User Metrics for Telemetry\u003c/strong\u003e: Gain valuable insights into usage patterns and platform engagement with new metrics tracking active and total users—enhancing auditability and planning for large organizations.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eTraceability with Log Trace and Span IDs\u003c/strong\u003e: Each log entry now carries detailed trace and span IDs, making it much easier for admins to pinpoint and resolve issues across distributed systems or in complex troubleshooting.\u003c/li\u003e\n\u003cli\u003e👥 \u003cstrong\u003eUser Group Add/Remove Endpoints\u003c/strong\u003e: Effortlessly add or remove users from groups with new, improved endpoints—giving admins and team leads faster, clearer control over collaboration and permissions.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eNote Settings and Controls Streamlined\u003c/strong\u003e: The main “Settings” for notes are now simply called “Controls”, and note files now reside in a dedicated controls section, decluttering navigation and making it easier to find and configure note-related options.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eFaster Admin User Page Loads\u003c/strong\u003e: The user list endpoint for admins has been optimized to exclude heavy profile images, speeding up load times for large teams and reducing waiting during administrative tasks.\u003c/li\u003e\n\u003cli\u003e📡 \u003cstrong\u003eChat ID Header Forwarding\u003c/strong\u003e: Ollama and OpenAI router requests now include the chat ID in request headers, enabling better request correlation and debugging capabilities across AI model integrations.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEnhanced Reasoning Tag Processing\u003c/strong\u003e: Improved and expanded reasoning tag parsing to handle various tag formats more robustly, including standard XML-style tags and custom delimiters, ensuring better AI reasoning transparency and debugging capabilities.\u003c/li\u003e\n\u003cli\u003e🔐 \u003cstrong\u003eOAuth Token Endpoint Authentication Method\u003c/strong\u003e: Added configurable OAuth token endpoint authentication method support, providing enhanced flexibility and security options for enterprise OAuth integrations and identity provider compatibility.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRedis Sentinel High Availability Support\u003c/strong\u003e: Comprehensive Redis Sentinel failover implementation with automatic master discovery, intelligent retry logic for connection failures, and seamless operation during master node outages—eliminating single points of failure and ensuring continuous service availability in production deployments.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eLocalization \u0026amp; Internationalization Improvements\u003c/strong\u003e: Refined and expanded translations for Simplified Chinese, Traditional Chinese, French, German, Korean, and Polish, ensuring a more fluent and native experience for global users across all supported languages.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eHybrid Search Functionality Restored\u003c/strong\u003e: Hybrid search now works seamlessly again—enabling more accurate, relevant, and comprehensive knowledge discovery across all RAG-powered workflows.\u003c/li\u003e\n\u003cli\u003e🚦 \u003cstrong\u003eNote Chat - Edit Button Disabled During AI Generation\u003c/strong\u003e: The edit button when chatting with a note is now disabled while the AI is responding—preventing accidental edits and ensuring workflow clarity during chat sessions.\u003c/li\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eCleaner Database Credentials\u003c/strong\u003e: Database connection no longer duplicates ‘@’ in credentials, preventing potential connection issues and ensuring smoother, more reliable integrations.\u003c/li\u003e\n\u003cli\u003e🧑‍💻 \u003cstrong\u003eFile Deletion Now Removes Related Vector Data\u003c/strong\u003e: When files are deleted from storage, they are now purged from the vector database as well, ensuring clean data management and preventing clutter or stale search results.\u003c/li\u003e\n\u003cli\u003e📁 \u003cstrong\u003eFiles Modal Translation Issues Fixed\u003c/strong\u003e: All modal dialog strings—including “Using Entire Document” and “Using Focused Retrieval”—are now fully translated for a more consistent and localized UI experience.\u003c/li\u003e\n\u003cli\u003e🚫 \u003cstrong\u003eDrag-and-Drop File Upload Disabled for Unsupported Models\u003c/strong\u003e: File upload by drag-and-drop is disabled when using models that do not support attachments—removing confusion and preventing workflow interruptions.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eOllama Tool Calls Now Reliable\u003c/strong\u003e: Fixed issues with Ollama-based tool calls, ensuring uninterrupted AI augmentation and tool use for every chat.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eMIME Type Help String Correction\u003c/strong\u003e: Cleaned up mimetype help text by removing extraneous characters, providing clearer guidance for file upload configurations.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eNote Editor Permission Fix\u003c/strong\u003e: Removed unnecessary admin-only restriction from note chat functionality, allowing all authorized users to access note editing features as intended.\u003c/li\u003e\n\u003cli\u003e📋 \u003cstrong\u003eChat Sources Handling Improved\u003c/strong\u003e: Fixed sources handling logic to prevent duplicate source assignments in chat messages, ensuring cleaner and more accurate source attribution during conversations.\u003c/li\u003e\n\u003cli\u003e😀 \u003cstrong\u003eEmoji Generation Error Handling\u003c/strong\u003e: Improved error handling in audio router and fixed metadata structure for emoji generation tasks, preventing crashes and ensuring more reliable emoji generation functionality.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eFolder System Prompt Permission Enforcement\u003c/strong\u003e: System prompt fields in folder edit modal are now properly hidden for users without system prompt permissions, ensuring consistent security policy enforcement across all folder management interfaces.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eWebSocket Redis Lock Timeout Type Conversion\u003c/strong\u003e: Fixed proper integer type conversion for WebSocket Redis lock timeout configuration with robust error handling, preventing potential configuration errors and ensuring stable WebSocket connections.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003ePostHog Dependency Added\u003c/strong\u003e: Added PostHog 5.4.0 library to resolve ChromaDB compatibility issues, ensuring stable vector database operations and preventing library version conflicts during deployment.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/5fbfe2bdcadf5f157926f6551891e4dc0802b9f3\"\u003e\u003ccode\u003e5fbfe2b\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15879\"\u003e#15879\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/6e0328798db704418391dd0ee2a631c41f8f507e\"\u003e\u003ccode\u003e6e03287\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/0119036a117cdd4da6749b6cd043b8aa2a212c8b\"\u003e\u003ccode\u003e0119036\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15871\"\u003e#15871\u003c/a\u003e from Classic298/cors\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7a023e0841076e53f388b60cae37443adcffbd6f\"\u003e\u003ccode\u003e7a023e0\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15875\"\u003e#15875\u003c/a\u003e from leebeomhun/i18n-ko\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b397008ee06993814ea85dfde1e2cbc6380eab01\"\u003e\u003ccode\u003eb397008\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b329c63c80ff092e7894b1f4769c4d9a73668a35\"\u003e\u003ccode\u003eb329c63\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/95b11207a12d7811dfc0b78bf082e50c43ffc693\"\u003e\u003ccode\u003e95b1120\u003c/code\u003e\u003c/a\u003e fix: group user load\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/74d0e6b2c7501026153d56e44b2d64b5b1499720\"\u003e\u003ccode\u003e74d0e6b\u003c/code\u003e\u003c/a\u003e i18n korean Fix typo\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7ffc12567f81d47a761afc64131c809cc094905a\"\u003e\u003ccode\u003e7ffc125\u003c/code\u003e\u003c/a\u003e i18n update and fix:ko-KR translation.json\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d8ed4fa0c270ba1ecba08362a4e52204b9c65b80\"\u003e\u003ccode\u003ed8ed4fa\u003c/code\u003e\u003c/a\u003e Merge branch 'open-webui:main' into cors\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.18\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=0.6.18)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/76","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/76","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/76/packages"}},{"old_version":"v0.5.20","new_version":"v0.6.16","update_type":"minor","path":"/docker","pr_created_at":"2025-07-14T22:33:35.000Z","version_change":"v0.5.20 → v0.6.16","issue":{"uuid":"2665558087","node_id":"PR_kwDOM-FVBM6e4TBH","number":75,"state":"open","title":"Bump open-webui/open-webui from v0.5.20 to v0.6.16 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-07-14T22:33:35.000Z","updated_at":"2025-07-14T22:33:35.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"v0.6.16","repository_url":null}],"path":"/docker","ecosystem":"docker"},"body":"\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=v0.6.16)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/75","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/75","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/75/packages"}},{"old_version":"`4583b43`","new_version":"`07d6e7b`","update_type":null,"path":null,"pr_created_at":"2025-07-01T22:18:24.000Z","version_change":"`4583b43` → `07d6e7b`","issue":{"uuid":"2633773563","node_id":"PR_kwDONjNt7s6c_DH7","number":6,"state":"open","title":"Bump open-webui/open-webui from `4583b43` to `07d6e7b`","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-07-01T22:18:24.000Z","updated_at":"2025-07-01T22:18:25.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"`4583b43`","new_version":"`07d6e7b`","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from `4583b43` to `07d6e7b`.\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch1\u003eChangelog\u003c/h1\u003e\n\u003cp\u003eAll notable changes to this project will be documented in this file.\u003c/p\u003e\n\u003cp\u003eThe format is based on \u003ca href=\"https://keepachangelog.com/en/1.1.0/\"\u003eKeep a Changelog\u003c/a\u003e,\nand this project adheres to \u003ca href=\"https://semver.org/spec/v2.0.0.html\"\u003eSemantic Versioning\u003c/a\u003e.\u003c/p\u003e\n\u003ch2\u003e[0.6.15] - 2025-06-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eGlobal Image Compression Option\u003c/strong\u003e: Effortlessly set image compression globally so all image uploads and outputs are optimized, speeding up load times and saving bandwidth—perfect for teams dealing with large files or limited network resources.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eCustom Speech-to-Text Content-Type for Transcription\u003c/strong\u003e: Define custom content types for audio transcription, ensuring compatibility with diverse audio sources and unlocking smoother, more accurate transcriptions in advanced setups.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLDAP Group Synchronization (Experimental)\u003c/strong\u003e: Automatically sync user groups from your LDAP directory directly into Open WebUI for seamless enterprise access management—simplifies identity integration and governance across your organization.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eOpenTelemetry Metrics via OTLP Exporter (Experimental)\u003c/strong\u003e: Gain enterprise-grade analytics and monitor your AI usage in real time with experimental OpenTelemetry Metrics support—connect to any OTLP-compatible backend for instant insights into performance, load, and user interactions.\u003c/li\u003e\n\u003cli\u003e🕰️ \u003cstrong\u003eSee User Message Timestamps on Hover (Chat Bubble UI)\u003c/strong\u003e: Effortlessly check when any user message was sent by hovering over it in Chat Bubble mode—no more switching screens or digging through logs for context.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLeaderboard Sorting Options\u003c/strong\u003e: Sort the leaderboard directly in the UI for a clearer, more actionable view of top performers, models, or tools—making analysis and recognition quick and easy for teams.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eEvaluation Details Modal in Feedbacks and Leaderboard\u003c/strong\u003e: Dive deeper with new modals that display detailed evaluation information when reviewing feedbacks and leaderboard rankings—accelerates learning, progress tracking, and quality improvement.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSupport for Multiple Pages in External Document Loaders\u003c/strong\u003e: Effortlessly extract and work with content spanning multiple pages in external documents, giving you complete flexibility for in-depth research and document workflows.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eNew Accessibility Enhancements Across the Interface\u003c/strong\u003e: Benefit from significant accessibility improvements—tab navigation, ARIA roles/labels, better high-contrast text/modes, accessible modals, and more—making Open WebUI more usable and equitable for everyone, including those using assistive technologies.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePerformance \u0026amp; Stability Upgrades Across Frontend and Backend\u003c/strong\u003e: Enjoy a smoother, more reliable experience with numerous behind-the-scenes optimizations and refactoring on both frontend and backend—resulting in faster load times, fewer errors, and even greater stability throughout your workflows.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eUpdated and Expanded Localizations\u003c/strong\u003e: Enjoy improved, up-to-date translations for Finnish, German (now with model pinning features), Korean, Russian, Simplified Chinese, Spanish, and more—making every interaction smoother, clearer, and more intuitive for international users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🦾 \u003cstrong\u003eOllama Error Messages More Descriptive\u003c/strong\u003e: Receive clearer, more actionable error messages when something goes wrong with Ollama models—making troubleshooting and user support faster and more effective.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Webloader Now Works as Expected\u003c/strong\u003e: Resolved an issue where the \u0026quot;bypass webloader\u0026quot; feature failed to function correctly, ensuring web search bypasses operate smoothly and reliably for lighter, faster query results.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003ePrevent Redundant Documents in Citation List\u003c/strong\u003e: The expanded citation list no longer shows duplicate documents, offering a cleaner, easier-to-digest reference experience when reviewing sources in knowledge and research workflows.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eTrusted Header Email Matching is Now Case-Insensitive\u003c/strong\u003e: Fixed a critical authentication issue where email case sensitivity could cause secure headers to mismatch, ensuring robust, seamless login and session management in all environments.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eDirect Tool Server Input Accepts Empty Strings\u003c/strong\u003e: You can now submit direct tool server commands without unexpected errors when passing empty-string values, improving integration and automation efficiency.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eCitation Page Number for Page 1 is Now Displayed\u003c/strong\u003e: Corrected an oversight where references for page 1 documents were missing the page number; citations are now always accurate and fully visible.\u003c/li\u003e\n\u003cli\u003e📒 \u003cstrong\u003eNotes Access Restored\u003c/strong\u003e: Fixed an issue where some users could not access their notes—everyone can now view and manage their notes reliably, ensuring seamless documentation and workflow continuity.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eOAuth Callback Double-Slash Issue Resolved\u003c/strong\u003e: Fixed rare cases where an extra slash in OAuth callbacks caused failed logins or redirects, making third-party login integrations more reliable.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eDedicated Permission for System Prompts\u003c/strong\u003e: System prompt access is now controlled by its own specific permission instead of being grouped with general chat controls, empowering admins with finer-grained management over who can view or modify system prompts for enhanced security and workflow customization.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eYouTube Transcript API and python-pptx Updated\u003c/strong\u003e: Enjoy better performance, reliability, and broader compatibility thanks to underlying library upgrades—less friction with media-rich and presentation workflows.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eConsole Logging Disabled in Production\u003c/strong\u003e: All 'console.log' and 'console.debug' statements are now disabled in production, guaranteeing improved security and cleaner browser logs for end users by removing extraneous technical output.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003eSee full diff in \u003ca href=\"https://github.com/open-webui/open-webui/commits\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=main\u0026new-version=main)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/ArloL/open-webui-runner/pull/6","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArloL%2Fopen-webui-runner/issues/6","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/6/packages"}},{"old_version":"v0.5.20","new_version":"0.6.15","update_type":"minor","path":"/docker","pr_created_at":"2025-06-16T20:46:37.000Z","version_change":"v0.5.20 → 0.6.15","issue":{"uuid":"3151274888","node_id":"PR_kwDOM-FVBM6ayQz0","number":68,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to 0.6.15 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-07-14T22:33:37.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-06-16T20:46:37.000Z","updated_at":"2025-07-14T22:33:37.000Z","time_to_close":2425620,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"0.6.15","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to 0.6.15.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.15\u003c/h2\u003e\n\u003ch2\u003e[0.6.15] - 2025-06-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eGlobal Image Compression Option\u003c/strong\u003e: Effortlessly set image compression globally so all image uploads and outputs are optimized, speeding up load times and saving bandwidth—perfect for teams dealing with large files or limited network resources.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eCustom Speech-to-Text Content-Type for Transcription\u003c/strong\u003e: Define custom content types for audio transcription, ensuring compatibility with diverse audio sources and unlocking smoother, more accurate transcriptions in advanced setups.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLDAP Group Synchronization (Experimental)\u003c/strong\u003e: Automatically sync user groups from your LDAP directory directly into Open WebUI for seamless enterprise access management—simplifies identity integration and governance across your organization.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eOpenTelemetry Metrics via OTLP Exporter (Experimental)\u003c/strong\u003e: Gain enterprise-grade analytics and monitor your AI usage in real time with experimental OpenTelemetry Metrics support—connect to any OTLP-compatible backend for instant insights into performance, load, and user interactions.\u003c/li\u003e\n\u003cli\u003e🕰️ \u003cstrong\u003eSee User Message Timestamps on Hover (Chat Bubble UI)\u003c/strong\u003e: Effortlessly check when any user message was sent by hovering over it in Chat Bubble mode—no more switching screens or digging through logs for context.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLeaderboard Sorting Options\u003c/strong\u003e: Sort the leaderboard directly in the UI for a clearer, more actionable view of top performers, models, or tools—making analysis and recognition quick and easy for teams.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eEvaluation Details Modal in Feedbacks and Leaderboard\u003c/strong\u003e: Dive deeper with new modals that display detailed evaluation information when reviewing feedbacks and leaderboard rankings—accelerates learning, progress tracking, and quality improvement.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSupport for Multiple Pages in External Document Loaders\u003c/strong\u003e: Effortlessly extract and work with content spanning multiple pages in external documents, giving you complete flexibility for in-depth research and document workflows.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eNew Accessibility Enhancements Across the Interface\u003c/strong\u003e: Benefit from significant accessibility improvements—tab navigation, ARIA roles/labels, better high-contrast text/modes, accessible modals, and more—making Open WebUI more usable and equitable for everyone, including those using assistive technologies.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePerformance \u0026amp; Stability Upgrades Across Frontend and Backend\u003c/strong\u003e: Enjoy a smoother, more reliable experience with numerous behind-the-scenes optimizations and refactoring on both frontend and backend—resulting in faster load times, fewer errors, and even greater stability throughout your workflows.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eUpdated and Expanded Localizations\u003c/strong\u003e: Enjoy improved, up-to-date translations for Finnish, German (now with model pinning features), Korean, Russian, Simplified Chinese, Spanish, and more—making every interaction smoother, clearer, and more intuitive for international users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🦾 \u003cstrong\u003eOllama Error Messages More Descriptive\u003c/strong\u003e: Receive clearer, more actionable error messages when something goes wrong with Ollama models—making troubleshooting and user support faster and more effective.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Webloader Now Works as Expected\u003c/strong\u003e: Resolved an issue where the \u0026quot;bypass webloader\u0026quot; feature failed to function correctly, ensuring web search bypasses operate smoothly and reliably for lighter, faster query results.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003ePrevent Redundant Documents in Citation List\u003c/strong\u003e: The expanded citation list no longer shows duplicate documents, offering a cleaner, easier-to-digest reference experience when reviewing sources in knowledge and research workflows.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eTrusted Header Email Matching is Now Case-Insensitive\u003c/strong\u003e: Fixed a critical authentication issue where email case sensitivity could cause secure headers to mismatch, ensuring robust, seamless login and session management in all environments.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eDirect Tool Server Input Accepts Empty Strings\u003c/strong\u003e: You can now submit direct tool server commands without unexpected errors when passing empty-string values, improving integration and automation efficiency.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eCitation Page Number for Page 1 is Now Displayed\u003c/strong\u003e: Corrected an oversight where references for page 1 documents were missing the page number; citations are now always accurate and fully visible.\u003c/li\u003e\n\u003cli\u003e📒 \u003cstrong\u003eNotes Access Restored\u003c/strong\u003e: Fixed an issue where some users could not access their notes—everyone can now view and manage their notes reliably, ensuring seamless documentation and workflow continuity.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eOAuth Callback Double-Slash Issue Resolved\u003c/strong\u003e: Fixed rare cases where an extra slash in OAuth callbacks caused failed logins or redirects, making third-party login integrations more reliable.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eDedicated Permission for System Prompts\u003c/strong\u003e: System prompt access is now controlled by its own specific permission instead of being grouped with general chat controls, empowering admins with finer-grained management over who can view or modify system prompts for enhanced security and workflow customization.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eYouTube Transcript API and python-pptx Updated\u003c/strong\u003e: Enjoy better performance, reliability, and broader compatibility thanks to underlying library upgrades—less friction with media-rich and presentation workflows.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eConsole Logging Disabled in Production\u003c/strong\u003e: All 'console.log' and 'console.debug' statements are now disabled in production, guaranteeing improved security and cleaner browser logs for end users by removing extraneous technical output.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:\n\u003ca href=\"https://github.com/SadmL\"\u003e\u003ccode\u003e@​SadmL\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Bek85\"\u003e\u003ccode\u003e@​Bek85\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/vaclcer\"\u003e\u003ccode\u003e@​vaclcer\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/2underscores\"\u003e\u003ccode\u003e@​2underscores\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Ithanil\"\u003e\u003ccode\u003e@​Ithanil\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/ayanahye\"\u003e\u003ccode\u003e@​ayanahye\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/qingchunnh\"\u003e\u003ccode\u003e@​qingchunnh\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Kylapaallikko\"\u003e\u003ccode\u003e@​Kylapaallikko\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/silentoplayz\"\u003e\u003ccode\u003e@​silentoplayz\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/t-rekttt\"\u003e\u003ccode\u003e@​t-rekttt\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/jk-f5\"\u003e\u003ccode\u003e@​jk-f5\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/tcx4c70\"\u003e\u003ccode\u003e@​tcx4c70\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/williamgateszhao\"\u003e\u003ccode\u003e@​williamgateszhao\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/rgaricano\"\u003e\u003ccode\u003e@​rgaricano\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/sreesdas\"\u003e\u003ccode\u003e@​sreesdas\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Classic298\"\u003e\u003ccode\u003e@​Classic298\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/jackthgu\"\u003e\u003ccode\u003e@​jackthgu\u003c/code\u003e\u003c/a\u003e\u003c/p\u003e\n\u003ch2\u003eSponsors 🙌\u003c/h2\u003e\n\u003cp\u003e🚀 We'd like to extend a heartfelt thank you to our amazing sponsors for their generous support (Note: We've excluded private sponsors from this list. If you'd like to get featured here, feel free to reach out to us!)\u003c/p\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.15] - 2025-06-16\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🖼️ \u003cstrong\u003eGlobal Image Compression Option\u003c/strong\u003e: Effortlessly set image compression globally so all image uploads and outputs are optimized, speeding up load times and saving bandwidth—perfect for teams dealing with large files or limited network resources.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eCustom Speech-to-Text Content-Type for Transcription\u003c/strong\u003e: Define custom content types for audio transcription, ensuring compatibility with diverse audio sources and unlocking smoother, more accurate transcriptions in advanced setups.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLDAP Group Synchronization (Experimental)\u003c/strong\u003e: Automatically sync user groups from your LDAP directory directly into Open WebUI for seamless enterprise access management—simplifies identity integration and governance across your organization.\u003c/li\u003e\n\u003cli\u003e📈 \u003cstrong\u003eOpenTelemetry Metrics via OTLP Exporter (Experimental)\u003c/strong\u003e: Gain enterprise-grade analytics and monitor your AI usage in real time with experimental OpenTelemetry Metrics support—connect to any OTLP-compatible backend for instant insights into performance, load, and user interactions.\u003c/li\u003e\n\u003cli\u003e🕰️ \u003cstrong\u003eSee User Message Timestamps on Hover (Chat Bubble UI)\u003c/strong\u003e: Effortlessly check when any user message was sent by hovering over it in Chat Bubble mode—no more switching screens or digging through logs for context.\u003c/li\u003e\n\u003cli\u003e🗂️ \u003cstrong\u003eLeaderboard Sorting Options\u003c/strong\u003e: Sort the leaderboard directly in the UI for a clearer, more actionable view of top performers, models, or tools—making analysis and recognition quick and easy for teams.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eEvaluation Details Modal in Feedbacks and Leaderboard\u003c/strong\u003e: Dive deeper with new modals that display detailed evaluation information when reviewing feedbacks and leaderboard rankings—accelerates learning, progress tracking, and quality improvement.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eSupport for Multiple Pages in External Document Loaders\u003c/strong\u003e: Effortlessly extract and work with content spanning multiple pages in external documents, giving you complete flexibility for in-depth research and document workflows.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eNew Accessibility Enhancements Across the Interface\u003c/strong\u003e: Benefit from significant accessibility improvements—tab navigation, ARIA roles/labels, better high-contrast text/modes, accessible modals, and more—making Open WebUI more usable and equitable for everyone, including those using assistive technologies.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003ePerformance \u0026amp; Stability Upgrades Across Frontend and Backend\u003c/strong\u003e: Enjoy a smoother, more reliable experience with numerous behind-the-scenes optimizations and refactoring on both frontend and backend—resulting in faster load times, fewer errors, and even greater stability throughout your workflows.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eUpdated and Expanded Localizations\u003c/strong\u003e: Enjoy improved, up-to-date translations for Finnish, German (now with model pinning features), Korean, Russian, Simplified Chinese, Spanish, and more—making every interaction smoother, clearer, and more intuitive for international users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🦾 \u003cstrong\u003eOllama Error Messages More Descriptive\u003c/strong\u003e: Receive clearer, more actionable error messages when something goes wrong with Ollama models—making troubleshooting and user support faster and more effective.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Webloader Now Works as Expected\u003c/strong\u003e: Resolved an issue where the \u0026quot;bypass webloader\u0026quot; feature failed to function correctly, ensuring web search bypasses operate smoothly and reliably for lighter, faster query results.\u003c/li\u003e\n\u003cli\u003e🔍 \u003cstrong\u003ePrevent Redundant Documents in Citation List\u003c/strong\u003e: The expanded citation list no longer shows duplicate documents, offering a cleaner, easier-to-digest reference experience when reviewing sources in knowledge and research workflows.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eTrusted Header Email Matching is Now Case-Insensitive\u003c/strong\u003e: Fixed a critical authentication issue where email case sensitivity could cause secure headers to mismatch, ensuring robust, seamless login and session management in all environments.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eDirect Tool Server Input Accepts Empty Strings\u003c/strong\u003e: You can now submit direct tool server commands without unexpected errors when passing empty-string values, improving integration and automation efficiency.\u003c/li\u003e\n\u003cli\u003e📄 \u003cstrong\u003eCitation Page Number for Page 1 is Now Displayed\u003c/strong\u003e: Corrected an oversight where references for page 1 documents were missing the page number; citations are now always accurate and fully visible.\u003c/li\u003e\n\u003cli\u003e📒 \u003cstrong\u003eNotes Access Restored\u003c/strong\u003e: Fixed an issue where some users could not access their notes—everyone can now view and manage their notes reliably, ensuring seamless documentation and workflow continuity.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eOAuth Callback Double-Slash Issue Resolved\u003c/strong\u003e: Fixed rare cases where an extra slash in OAuth callbacks caused failed logins or redirects, making third-party login integrations more reliable.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eChanged\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eDedicated Permission for System Prompts\u003c/strong\u003e: System prompt access is now controlled by its own specific permission instead of being grouped with general chat controls, empowering admins with finer-grained management over who can view or modify system prompts for enhanced security and workflow customization.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eYouTube Transcript API and python-pptx Updated\u003c/strong\u003e: Enjoy better performance, reliability, and broader compatibility thanks to underlying library upgrades—less friction with media-rich and presentation workflows.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eConsole Logging Disabled in Production\u003c/strong\u003e: All 'console.log' and 'console.debug' statements are now disabled in production, guaranteeing improved security and cleaner browser logs for end users by removing extraneous technical output.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eSelector Model Item Menu\u003c/strong\u003e: Each model in the selector now features a menu where you can easily pin/unpin to the sidebar and copy a direct link—simplifying collaboration and staying organized in even the busiest environments.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eReliable Stop for Ongoing Chats in Multi-Replica Setups\u003c/strong\u003e: Stopping or cancelling an in-progress chat now works reliably even in clustered deployments—ensuring every user can interrupt AI output at any time, no matter your scale.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003e'Think' Parameter for Ollama Models\u003c/strong\u003e: Leverage new 'think' parameter support for Ollama—giving you advanced control over AI reasoning process and further tuning model behavior for your unique use cases.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003ePicture Description Modes for Docling\u003c/strong\u003e: Customize how images are described/extracted by Docling Loader for smarter, more detailed, and workflow-tailored image understanding in your document pipelines.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eSettings Modal Deep Linking\u003c/strong\u003e: Every tab in Settings now has its own route—making direct navigation and sharing of precise settings faster and more intuitive.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eAudio HTML Component Token\u003c/strong\u003e: Easily embed and play audio directly in your chats, improving voice-based workflows and making audio content instantly accessible and manageable from any conversation.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eSupport for Secret Key File\u003c/strong\u003e: Now you can specify 'WEBUI_SECRET_KEY_FILE' for more secure and flexible key management—ideal for advanced deployments and tighter security standards.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b5f4c85bb196c16a775802907aedd87366f58b0f\"\u003e\u003ccode\u003eb5f4c85\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15014\"\u003e#15014\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/340d9820b8122035258d6931cd22f1be0a716c74\"\u003e\u003ccode\u003e340d982\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/597709c64c5f09ae8c6f069ed8e6f5a09cd8ed35\"\u003e\u003ccode\u003e597709c\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/84fd41e6eff8ff301d1224936898fce196ccb6b6\"\u003e\u003ccode\u003e84fd41e\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/3917b04ed3554d776cdbdd97b25be619ff989a8a\"\u003e\u003ccode\u003e3917b04\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b6ea043d18930f9d32382708aa58d9c44803979b\"\u003e\u003ccode\u003eb6ea043\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b082a7edbe9f33632c5959928fbd3aa21c5817be\"\u003e\u003ccode\u003eb082a7e\u003c/code\u003e\u003c/a\u003e enh: allow iframe in content\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/72df23ed79b74036480ea45735350a04b6c6456b\"\u003e\u003ccode\u003e72df23e\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/11476eb6eee96d98747eb978b39f8a620db1a849\"\u003e\u003ccode\u003e11476eb\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7096baff1b09e9fcaf498ffc626bf44dd65de162\"\u003e\u003ccode\u003e7096baf\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/15021\"\u003e#15021\u003c/a\u003e from rgaricano/dev\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.15\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=0.6.15)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/68","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/68","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/68/packages"}},{"old_version":"v0.5.20","new_version":"0.6.14","update_type":"minor","path":"/docker","pr_created_at":"2025-06-10T19:46:22.000Z","version_change":"v0.5.20 → 0.6.14","issue":{"uuid":"3134676705","node_id":"PR_kwDOM-FVBM6Z61_G","number":67,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to 0.6.14 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-06-16T20:46:39.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-06-10T19:46:22.000Z","updated_at":"2025-06-16T20:46:39.000Z","time_to_close":522017,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"0.6.14","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to 0.6.14.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.14\u003c/h2\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eSelector Model Item Menu\u003c/strong\u003e: Each model in the selector now features a menu where you can easily pin/unpin to the sidebar and copy a direct link—simplifying collaboration and staying organized in even the busiest environments.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eReliable Stop for Ongoing Chats in Multi-Replica Setups\u003c/strong\u003e: Stopping or cancelling an in-progress chat now works reliably even in clustered deployments—ensuring every user can interrupt AI output at any time, no matter your scale.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003e'Think' Parameter for Ollama Models\u003c/strong\u003e: Leverage new 'think' parameter support for Ollama—giving you advanced control over AI reasoning process and further tuning model behavior for your unique use cases.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003ePicture Description Modes for Docling\u003c/strong\u003e: Customize how images are described/extracted by Docling Loader for smarter, more detailed, and workflow-tailored image understanding in your document pipelines.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eSettings Modal Deep Linking\u003c/strong\u003e: Every tab in Settings now has its own route—making direct navigation and sharing of precise settings faster and more intuitive.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eAudio HTML Component Token\u003c/strong\u003e: Easily embed and play audio directly in your chats, improving voice-based workflows and making audio content instantly accessible and manageable from any conversation.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eSupport for Secret Key File\u003c/strong\u003e: Now you can specify 'WEBUI_SECRET_KEY_FILE' for more secure and flexible key management—ideal for advanced deployments and tighter security standards.\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eClarity When Cloning Prompts\u003c/strong\u003e: Cloned workspace prompts are clearly labelled with \u0026quot;(Clone)\u0026quot; and IDs have \u0026quot;-clone\u0026quot;, keeping your prompt library organized and preventing accidental overwrites.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eDedicated User Role Edit Modal\u003c/strong\u003e: Updating user roles now reliably opens a dedicated edit user modal instead of cycling through roles—making it safer and more clear to manage team permissions.\u003c/li\u003e\n\u003cli\u003e🏞️ \u003cstrong\u003eBetter Handling \u0026amp; Storage of Interpreter-Generated Images\u003c/strong\u003e: Code interpreter-generated images are now centrally stored and reliably loaded from the database or cloud storage, ensuring your artifacts are always available.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003ePinecone \u0026amp; Vector Search Optimizations\u003c/strong\u003e: Applied latest best practices from Pinecone for smarter timeouts, intelligent retry control, improved connection pooling, faster DNS, and concurrent batch handling—giving you more reliable, faster document search and RAG performance without manual tweaks.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eOllama Advanced Parameters Unified\u003c/strong\u003e: 'keep_alive' and 'format' options are now integrated into the advanced params section—edit everything from the model editor for flexible model control.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eCUDA 12.6 Docker Image Support\u003c/strong\u003e: Deploy to NVIDIA GPUs with capability 7.0 and below (e.g., V100, GTX1080) via new cuda126 image—broadening your hardware options for scalable AI workloads.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eExperimental Table-Level PGVector Data Encryption\u003c/strong\u003e: Activate pgcrypto encryption support for pgvector to secure your vector search table contents, giving organizations enhanced compliance and data protection—perfect for enterprise or regulated environments.\u003c/li\u003e\n\u003cli\u003e👁 \u003cstrong\u003eAccessibility Upgrades Across Interface\u003c/strong\u003e: Chat buttons and close controls are now labelled and structured for optimal accessibility support, ensuring smoother operation with assistive technologies.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eHigh-Contrast Mode Expansions\u003c/strong\u003e: High-contrast accessibility mode now also applies to menu items, tabs, and search input fields, offering a more readable experience for all users.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTooltip \u0026amp; Translation Clarity\u003c/strong\u003e: Improved translation and tooltip clarity, especially over radio buttons, making the UI more understandable for all users.\u003c/li\u003e\n\u003cli\u003e🔠 \u003cstrong\u003eGlobal Localization \u0026amp; Translation Improvements\u003c/strong\u003e: Hefty upgrades to Traditional Chinese, Simplified Chinese, Hebrew, Russian, Irish, German, and Danish translation packs—making the platform feel native and intuitive for even more users worldwide.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGeneral Backend Stability \u0026amp; Security Enhancements\u003c/strong\u003e: Refined numerous backend routines to minimize memory use, improve performance, and streamline integration with external APIs—making the entire platform more robust and secure for daily work.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷 \u003cstrong\u003eFeedback Score Display Improved\u003c/strong\u003e: Addressed overflow and visibility issues with feedback scores for more readable and accessible evaluations.\u003c/li\u003e\n\u003cli\u003e🗂 \u003cstrong\u003eAdmin Settings Model Edits Apply Immediately\u003c/strong\u003e: Changes made in the Model Editor within Admin Settings now take effect instantly, eliminating confusion during model management.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eAssigned Tools Update Instantly on New Chats\u003c/strong\u003e: Models assigned with specific tools now consistently update and are available in every new chat—making tool workflows more predictable and robust.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eDocument Settings Saved Only on User Action\u003c/strong\u003e: Document settings now save only when you press the Save button, reducing accidental changes and ensuring greater control.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eVoice Recording on Older iOS Devices Restored\u003c/strong\u003e: Voice input is now fully functional on older iOS devices, keeping voice workflows accessible to all users.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eTrusted Email Header Session Security\u003c/strong\u003e: User sessions now strictly verify the trusted email header matches the logged-in user's email, ensuring secure authentication and preventing accidental session switching.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConsistent User Signout on Email Mismatch\u003c/strong\u003e: When the trusted email in the header changes, you will now be properly signed out and redirected, safeguarding your session's integrity.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eGeneral Error \u0026amp; Content Validation Improvements\u003c/strong\u003e: Smarter error handling means clearer messages and fewer unnecessary retries—making batch uploads, document handling, and knowledge indexing more resilient.\u003c/li\u003e\n\u003cli\u003e🕵️ \u003cstrong\u003eBetter Feedback on Chat Title Edits\u003c/strong\u003e: Error messages now show clearly if problems occur while editing chat titles.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.14] - 2025-06-10\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🤖 \u003cstrong\u003eAutomatic \u0026quot;Follow Up\u0026quot; Suggestions\u003c/strong\u003e: Open WebUI now intelligently generates actionable \u0026quot;Follow Up\u0026quot; suggestions automatically with each message you send, helping you stay productive and inspired without interrupting your flow; you can always disable this in Settings if you prefer a distraction-free experience.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eOpenAI-Compatible Embeddings Endpoint\u003c/strong\u003e: Introducing a fully OpenAI-style '/api/embeddings' endpoint—now you can plug in OpenAI-style embeddings workflows with zero hassle, making integrations with external tools and platforms seamless and familiar.\u003c/li\u003e\n\u003cli\u003e↗️ \u003cstrong\u003eModel Pinning for Quick Access\u003c/strong\u003e: Pin your favorite or most-used models to the sidebar for instant selection—no more scrolling through long model lists; your go-to models are always visible and ready for fast access.\u003c/li\u003e\n\u003cli\u003e📌 \u003cstrong\u003eSelector Model Item Menu\u003c/strong\u003e: Each model in the selector now features a menu where you can easily pin/unpin to the sidebar and copy a direct link—simplifying collaboration and staying organized in even the busiest environments.\u003c/li\u003e\n\u003cli\u003e🛑 \u003cstrong\u003eReliable Stop for Ongoing Chats in Multi-Replica Setups\u003c/strong\u003e: Stopping or cancelling an in-progress chat now works reliably even in clustered deployments—ensuring every user can interrupt AI output at any time, no matter your scale.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003e'Think' Parameter for Ollama Models\u003c/strong\u003e: Leverage new 'think' parameter support for Ollama—giving you advanced control over AI reasoning process and further tuning model behavior for your unique use cases.\u003c/li\u003e\n\u003cli\u003e💬 \u003cstrong\u003ePicture Description Modes for Docling\u003c/strong\u003e: Customize how images are described/extracted by Docling Loader for smarter, more detailed, and workflow-tailored image understanding in your document pipelines.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eSettings Modal Deep Linking\u003c/strong\u003e: Every tab in Settings now has its own route—making direct navigation and sharing of precise settings faster and more intuitive.\u003c/li\u003e\n\u003cli\u003e🎤 \u003cstrong\u003eAudio HTML Component Token\u003c/strong\u003e: Easily embed and play audio directly in your chats, improving voice-based workflows and making audio content instantly accessible and manageable from any conversation.\u003c/li\u003e\n\u003cli\u003e🔑 \u003cstrong\u003eSupport for Secret Key File\u003c/strong\u003e: Now you can specify 'WEBUI_SECRET_KEY_FILE' for more secure and flexible key management—ideal for advanced deployments and tighter security standards.\u003c/li\u003e\n\u003cli\u003e💡 \u003cstrong\u003eClarity When Cloning Prompts\u003c/strong\u003e: Cloned workspace prompts are clearly labelled with \u0026quot;(Clone)\u0026quot; and IDs have \u0026quot;-clone\u0026quot;, keeping your prompt library organized and preventing accidental overwrites.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eDedicated User Role Edit Modal\u003c/strong\u003e: Updating user roles now reliably opens a dedicated edit user modal instead of cycling through roles—making it safer and more clear to manage team permissions.\u003c/li\u003e\n\u003cli\u003e🏞️ \u003cstrong\u003eBetter Handling \u0026amp; Storage of Interpreter-Generated Images\u003c/strong\u003e: Code interpreter-generated images are now centrally stored and reliably loaded from the database or cloud storage, ensuring your artifacts are always available.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003ePinecone \u0026amp; Vector Search Optimizations\u003c/strong\u003e: Applied latest best practices from Pinecone for smarter timeouts, intelligent retry control, improved connection pooling, faster DNS, and concurrent batch handling—giving you more reliable, faster document search and RAG performance without manual tweaks.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eOllama Advanced Parameters Unified\u003c/strong\u003e: 'keep_alive' and 'format' options are now integrated into the advanced params section—edit everything from the model editor for flexible model control.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eCUDA 12.6 Docker Image Support\u003c/strong\u003e: Deploy to NVIDIA GPUs with capability 7.0 and below (e.g., V100, GTX1080) via new cuda126 image—broadening your hardware options for scalable AI workloads.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eExperimental Table-Level PGVector Data Encryption\u003c/strong\u003e: Activate pgcrypto encryption support for pgvector to secure your vector search table contents, giving organizations enhanced compliance and data protection—perfect for enterprise or regulated environments.\u003c/li\u003e\n\u003cli\u003e👁 \u003cstrong\u003eAccessibility Upgrades Across Interface\u003c/strong\u003e: Chat buttons and close controls are now labelled and structured for optimal accessibility support, ensuring smoother operation with assistive technologies.\u003c/li\u003e\n\u003cli\u003e🎨 \u003cstrong\u003eHigh-Contrast Mode Expansions\u003c/strong\u003e: High-contrast accessibility mode now also applies to menu items, tabs, and search input fields, offering a more readable experience for all users.\u003c/li\u003e\n\u003cli\u003e🛠️ \u003cstrong\u003eTooltip \u0026amp; Translation Clarity\u003c/strong\u003e: Improved translation and tooltip clarity, especially over radio buttons, making the UI more understandable for all users.\u003c/li\u003e\n\u003cli\u003e🔠 \u003cstrong\u003eGlobal Localization \u0026amp; Translation Improvements\u003c/strong\u003e: Hefty upgrades to Traditional Chinese, Simplified Chinese, Hebrew, Russian, Irish, German, and Danish translation packs—making the platform feel native and intuitive for even more users worldwide.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGeneral Backend Stability \u0026amp; Security Enhancements\u003c/strong\u003e: Refined numerous backend routines to minimize memory use, improve performance, and streamline integration with external APIs—making the entire platform more robust and secure for daily work.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🏷 \u003cstrong\u003eFeedback Score Display Improved\u003c/strong\u003e: Addressed overflow and visibility issues with feedback scores for more readable and accessible evaluations.\u003c/li\u003e\n\u003cli\u003e🗂 \u003cstrong\u003eAdmin Settings Model Edits Apply Immediately\u003c/strong\u003e: Changes made in the Model Editor within Admin Settings now take effect instantly, eliminating confusion during model management.\u003c/li\u003e\n\u003cli\u003e🔄 \u003cstrong\u003eAssigned Tools Update Instantly on New Chats\u003c/strong\u003e: Models assigned with specific tools now consistently update and are available in every new chat—making tool workflows more predictable and robust.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eDocument Settings Saved Only on User Action\u003c/strong\u003e: Document settings now save only when you press the Save button, reducing accidental changes and ensuring greater control.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eVoice Recording on Older iOS Devices Restored\u003c/strong\u003e: Voice input is now fully functional on older iOS devices, keeping voice workflows accessible to all users.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eTrusted Email Header Session Security\u003c/strong\u003e: User sessions now strictly verify the trusted email header matches the logged-in user's email, ensuring secure authentication and preventing accidental session switching.\u003c/li\u003e\n\u003cli\u003e🔒 \u003cstrong\u003eConsistent User Signout on Email Mismatch\u003c/strong\u003e: When the trusted email in the header changes, you will now be properly signed out and redirected, safeguarding your session's integrity.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eGeneral Error \u0026amp; Content Validation Improvements\u003c/strong\u003e: Smarter error handling means clearer messages and fewer unnecessary retries—making batch uploads, document handling, and knowledge indexing more resilient.\u003c/li\u003e\n\u003cli\u003e🕵️ \u003cstrong\u003eBetter Feedback on Chat Title Edits\u003c/strong\u003e: Error messages now show clearly if problems occur while editing chat titles.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/63256136ef8322210c01c2bb322097d1ccfb8c6f\"\u003e\u003ccode\u003e6325613\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14675\"\u003e#14675\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/fd8cdb383c9ba37010c636e3937a13ab94044a94\"\u003e\u003ccode\u003efd8cdb3\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ab42a192e69140e0a417d669d166183ff7d9567b\"\u003e\u003ccode\u003eab42a19\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/adab4dbf218bf08ee22a05e658726a76871b9a05\"\u003e\u003ccode\u003eadab4db\u003c/code\u003e\u003c/a\u003e chore: bump\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/c14160d73af5375048fd84abe7fb153c03368cbf\"\u003e\u003ccode\u003ec14160d\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14845\"\u003e#14845\u003c/a\u003e from itk-dev/feature/accessibility-aria-label-close...\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a7330d97da59d0280ba95374d278df91af5620cb\"\u003e\u003ccode\u003ea7330d9\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b39d33cefbb58f35d29d4de9b743ba8637dfc2d5\"\u003e\u003ccode\u003eb39d33c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d2e7feea86b4fdbc0b4465133b3da664b7d33b70\"\u003e\u003ccode\u003ed2e7fee\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a018140c7d2b89b8fe02e5c0cf87cb59462f6df6\"\u003e\u003ccode\u003ea018140\u003c/code\u003e\u003c/a\u003e refac: admin settings models\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9931ccef1eb6448ea8df7949ca407acb040e428f\"\u003e\u003ccode\u003e9931cce\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.14\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=0.6.14)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/67","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/67","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/67/packages"}},{"old_version":"`3039364`","new_version":"`4583b43`","update_type":null,"path":null,"pr_created_at":"2025-06-01T22:51:30.000Z","version_change":"`3039364` → `4583b43`","issue":{"uuid":"2558734612","node_id":"PR_kwDONjNt7s6YgzEU","number":5,"state":"open","title":"Bump open-webui/open-webui from `3039364` to `4583b43`","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":0,"pull_request":true,"closed_at":null,"author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-06-01T22:51:30.000Z","updated_at":"2025-06-01T22:51:31.000Z","time_to_close":null,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"`3039364`","new_version":"`4583b43`","repository_url":"https://github.com/open-webui/open-webui"}],"path":null,"ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from `3039364` to `4583b43`.\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch1\u003eChangelog\u003c/h1\u003e\n\u003cp\u003eAll notable changes to this project will be documented in this file.\u003c/p\u003e\n\u003cp\u003eThe format is based on \u003ca href=\"https://keepachangelog.com/en/1.1.0/\"\u003eKeep a Changelog\u003c/a\u003e,\nand this project adheres to \u003ca href=\"https://semver.org/spec/v2.0.0.html\"\u003eSemantic Versioning\u003c/a\u003e.\u003c/p\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRobust Message Handling on Chat Load\u003c/strong\u003e: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCorrect Prompt Access Control\u003c/strong\u003e: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eOpen WebUI-Specific Params No Longer Sent to Models\u003c/strong\u003e: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmitted—restoring predictable, error-free model operation.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eRefined Memory Error Handling\u003c/strong\u003e: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your session—resulting in a more reliable, worry-free experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.11] - 2025-05-27\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟢 \u003cstrong\u003eOllama Model Status Indicator in Model Selector\u003c/strong\u003e: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003eSee full diff in \u003ca href=\"https://github.com/open-webui/open-webui/commits\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=main\u0026new-version=main)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/ArloL/open-webui-runner/pull/5","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArloL%2Fopen-webui-runner/issues/5","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/5/packages"}},{"old_version":"v0.5.20","new_version":"v0.6.13","update_type":"minor","path":"/docker","pr_created_at":"2025-05-30T19:21:26.000Z","version_change":"v0.5.20 → v0.6.13","issue":{"uuid":"2555504799","node_id":"PR_kwDOM-FVBM6YUeif","number":66,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to v0.6.13 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-06-10T19:46:24.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-05-30T19:21:26.000Z","updated_at":"2025-06-10T19:46:24.000Z","time_to_close":951898,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"v0.6.13","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to v0.6.13.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.13\u003c/h2\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRobust Message Handling on Chat Load\u003c/strong\u003e: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCorrect Prompt Access Control\u003c/strong\u003e: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eOpen WebUI-Specific Params No Longer Sent to Models\u003c/strong\u003e: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmitted—restoring predictable, error-free model operation.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eRefined Memory Error Handling\u003c/strong\u003e: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your session—resulting in a more reliable, worry-free experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003ev0.6.12\u003c/h2\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:\u003c/p\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.13] - 2025-05-30\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟦 \u003cstrong\u003eAzure OpenAI Embedding Support\u003c/strong\u003e: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflows—no more workarounds, connect and scale effortlessly.\u003c/li\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eSmarter Custom Parameter Handling\u003c/strong\u003e: Instantly enjoy more flexible model setup—any JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eGeneral Backend Refactoring\u003c/strong\u003e: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliability—making all your workflows run more smoothly.\u003c/li\u003e\n\u003cli\u003e🌏 \u003cstrong\u003eLocalization Upgrades\u003c/strong\u003e: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eRobust Message Handling on Chat Load\u003c/strong\u003e: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eCorrect Prompt Access Control\u003c/strong\u003e: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eOpen WebUI-Specific Params No Longer Sent to Models\u003c/strong\u003e: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmitted—restoring predictable, error-free model operation.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eRefined Memory Error Handling\u003c/strong\u003e: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your session—resulting in a more reliable, worry-free experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.11] - 2025-05-27\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟢 \u003cstrong\u003eOllama Model Status Indicator in Model Selector\u003c/strong\u003e: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eUnload Ollama Model Directly from Model Selector\u003c/strong\u003e: Easily release memory and resources by unloading any loaded Ollama model right in the model selector—streamline hardware management without switching pages.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eUser-Configurable Speech-to-Text Language Setting\u003c/strong\u003e: Improve transcription accuracy by letting individual users explicitly set their preferred STT language in their settings—ideal for multilingual teams and clear audio capture.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGranular Audio Playback Speed Control\u003c/strong\u003e: Instead of just presets, you can now choose granular audio speed using a numeric input, giving you complete control over playback pace in transcriptions and media reviews.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eGZip, Brotli, ZStd Compression Middleware\u003c/strong\u003e: Enjoy significantly faster page loads and reduced bandwidth usage with new server-side compression—giving users a snappier, more efficient experience.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eConfigurable Weight for BM25 in Hybrid Search\u003c/strong\u003e: Fine-tune search relevance by adjusting the weight for BM25 inside hybrid search from the UI, letting you tailor knowledge search results to your workflow.\u003c/li\u003e\n\u003cli\u003e🧪 \u003cstrong\u003eBypass File Creation with CTRL + SHIFT + V\u003c/strong\u003e: When “Paste Large Text as File” is enabled, use CTRL + SHIFT + V to skip the file creation dialog and instantly upload text as a file—perfect for rapid document prep.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Web Loader in Web Search\u003c/strong\u003e: Choose to bypass web content loading and use snippets directly in web search for faster, more reliable results when page loads are slow or blocked.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/53764fe64884da147359e54ed6d9607fe57f1600\"\u003e\u003ccode\u003e53764fe\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14486\"\u003e#14486\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/235489cfc55116e805ae8a3ee6a84efdcc1e40de\"\u003e\u003ccode\u003e235489c\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b2befd486fde81f49f10728affb139a96bd794d7\"\u003e\u003ccode\u003eb2befd4\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9306ae597238d956a9613f74e530dd61125e0cfa\"\u003e\u003ccode\u003e9306ae5\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/036ce12dd94c61f7f8751eb37afa3476c3068679\"\u003e\u003ccode\u003e036ce12\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/d6c3f93cfdacaab4340b7892ce2f0cb799c62cc2\"\u003e\u003ccode\u003ed6c3f93\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14509\"\u003e#14509\u003c/a\u003e from r0mdau/fix/audio-format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/b12a493fe5248d51ad755586e8a306d820ce9770\"\u003e\u003ccode\u003eb12a493\u003c/code\u003e\u003c/a\u003e fix: only trust codec_name for audio conversion\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/f4827f0c18d9df2c3cc5ebdb26ebe04148c3c8ae\"\u003e\u003ccode\u003ef4827f0\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/e1e2c096e298dd6bab5921ed1dd62d42f317f576\"\u003e\u003ccode\u003ee1e2c09\u003c/code\u003e\u003c/a\u003e refac: PLEASE follow existing convention\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ff353578dbf28040501e2cfe32add8a914059ddc\"\u003e\u003ccode\u003eff35357\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14370\"\u003e#14370\u003c/a\u003e from daw/feat/add-azure-openai-embeddings-option\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.13\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=v0.6.13)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/66","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/66","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/66/packages"}},{"old_version":"v0.5.20","new_version":"v0.6.12","update_type":"minor","path":"/docker","pr_created_at":"2025-05-29T19:37:05.000Z","version_change":"v0.5.20 → v0.6.12","issue":{"uuid":"2553068937","node_id":"PR_kwDOM-FVBM6YLL2J","number":64,"state":"closed","title":"Bump open-webui/open-webui from v0.5.20 to v0.6.12 in /docker","user":"dependabot[bot]","labels":["dependencies","docker"],"assignees":[],"locked":false,"comments_count":1,"pull_request":true,"closed_at":"2025-05-30T19:21:28.000Z","author_association":"CONTRIBUTOR","state_reason":null,"created_at":"2025-05-29T19:37:05.000Z","updated_at":"2025-05-30T19:21:28.000Z","time_to_close":85463,"merged_at":null,"merged_by":null,"closed_by":null,"dependency_metadata":{"prefix":"Bump","packages":[{"name":"open-webui/open-webui","old_version":"v0.5.20","new_version":"v0.6.12","repository_url":"https://github.com/open-webui/open-webui"}],"path":"/docker","ecosystem":"docker"},"body":"Bumps [open-webui/open-webui](https://github.com/open-webui/open-webui) from v0.5.20 to v0.6.12.\n\u003cdetails\u003e\n\u003csummary\u003eRelease notes\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/releases\"\u003eopen-webui/open-webui's releases\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003ev0.6.12\u003c/h2\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cblockquote\u003e\n\u003cp\u003e[!TIP]\u003cbr /\u003e\n\u003cstrong\u003eLooking for an \u003ca href=\"https://docs.openwebui.com/enterprise\"\u003eEnterprise Plan\u003c/a\u003e?\u003c/strong\u003e – \u003cstrong\u003e\u003ca href=\"https://github.com/open-webui/open-webui/blob/HEAD/mailto:sales@openwebui.com\"\u003eSpeak with Our Sales Team Today!\u003c/a\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGet \u003cstrong\u003eenhanced capabilities\u003c/strong\u003e, including \u003cstrong\u003ecustom theming and branding\u003c/strong\u003e, \u003cstrong\u003eService Level Agreement (SLA) support\u003c/strong\u003e, \u003cstrong\u003eLong-Term Support (LTS) versions\u003c/strong\u003e, and \u003cstrong\u003emore!\u003c/strong\u003e\u003c/p\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:\n\u003ca href=\"https://github.com/TiancongLx\"\u003e\u003ccode\u003e@​TiancongLx\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/SadmL\"\u003e\u003ccode\u003e@​SadmL\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Hisma\"\u003e\u003ccode\u003e@​Hisma\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Zyfax\"\u003e\u003ccode\u003e@​Zyfax\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/qingchunnh\"\u003e\u003ccode\u003e@​qingchunnh\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/NotYuSheng\"\u003e\u003ccode\u003e@​NotYuSheng\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/torisetxd\"\u003e\u003ccode\u003e@​torisetxd\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/hurxxxx\"\u003e\u003ccode\u003e@​hurxxxx\u003c/code\u003e\u003c/a\u003e\u003c/p\u003e\n\u003ch2\u003eSponsors 🙌\u003c/h2\u003e\n\u003cp\u003e🚀 We'd like to extend a heartfelt thank you to our amazing sponsors for their generous support (Note: We've excluded private sponsors from this list. If you'd like to get featured here, feel free to reach out to us!)\u003c/p\u003e\n\u003ch4\u003eEmerald\u003c/h4\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003en8n\u003c/strong\u003e \u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWarp\u003c/strong\u003e \u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c!-- raw HTML omitted --\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003ca href=\"https://github.com/amd\"\u003e\u003ccode\u003e@​amd\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/agency-agency\"\u003e\u003ccode\u003e@​agency-agency\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/roosi-gmbh\"\u003e\u003ccode\u003e@​roosi-gmbh\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Unsupervisedcom\"\u003e\u003ccode\u003e@​Unsupervisedcom\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/feddersen-group\"\u003e\u003ccode\u003e@​feddersen-group\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/SRKConsulting\"\u003e\u003ccode\u003e@​SRKConsulting\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/mushmax\"\u003e\u003ccode\u003e@​mushmax\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/rndmcnlly\"\u003e\u003ccode\u003e@​rndmcnlly\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/icanbwell\"\u003e\u003ccode\u003e@​icanbwell\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/blogic-cz\"\u003e\u003ccode\u003e@​blogic-cz\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Krambu-Travis\"\u003e\u003ccode\u003e@​Krambu-Travis\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/GenieDev101\"\u003e\u003ccode\u003e@​GenieDev101\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/PortlandKyGuy\"\u003e\u003ccode\u003e@​PortlandKyGuy\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/CubicleGangster\"\u003e\u003ccode\u003e@​CubicleGangster\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/GitDatamind\"\u003e\u003ccode\u003e@​GitDatamind\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/TOWaB\"\u003e\u003ccode\u003e@​TOWaB\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/TheZigGroup\"\u003e\u003ccode\u003e@​TheZigGroup\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/Classic298\"\u003e\u003ccode\u003e@​Classic298\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/comet-ml\"\u003e\u003ccode\u003e@​comet-ml\u003c/code\u003e\u003c/a\u003e, \u003ca href=\"https://github.com/chAyubTahir\"\u003e\u003ccode\u003e@​chAyubTahir\u003c/code\u003e\u003c/a\u003e\u003c/p\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eChangelog\u003c/summary\u003e\n\u003cp\u003e\u003cem\u003eSourced from \u003ca href=\"https://github.com/open-webui/open-webui/blob/main/CHANGELOG.md\"\u003eopen-webui/open-webui's changelog\u003c/a\u003e.\u003c/em\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003ch2\u003e[0.6.12] - 2025-05-29\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧩 \u003cstrong\u003eCustom Advanced Model Parameters\u003c/strong\u003e: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in options—accelerate your experimentation.\u003c/li\u003e\n\u003cli\u003e🪧 \u003cstrong\u003eDatalab Marker API Content Extraction Support\u003c/strong\u003e: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eParallelized Base Model Fetching\u003c/strong\u003e: Experience noticeably faster startup and model refresh times—base model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.\u003c/li\u003e\n\u003cli\u003e🧠 \u003cstrong\u003eEfficient Function Loading and Caching\u003c/strong\u003e: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eLocalization \u0026amp; Translation Enhancements\u003c/strong\u003e: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eFixed\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e💬 \u003cstrong\u003eStable Message Input Box\u003c/strong\u003e: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.\u003c/li\u003e\n\u003cli\u003e🔊 \u003cstrong\u003eReliable Read Aloud (Text-to-Speech)\u003c/strong\u003e: Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.\u003c/li\u003e\n\u003cli\u003e🖼 \u003cstrong\u003eImage Preview and Download Restored\u003c/strong\u003e: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chats—no more interruptions in creative or documentation workflows.\u003c/li\u003e\n\u003cli\u003e📱 \u003cstrong\u003eImproved Mobile Styling for Workspace Capabilities\u003c/strong\u003e: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.\u003c/li\u003e\n\u003cli\u003e🔁 \u003cstrong\u003e/api/v1/retrieval/query/collection Endpoint Reliability\u003c/strong\u003e: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3\u003eRemoved\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🧹 \u003cstrong\u003eDuplicate CSS Elements\u003c/strong\u003e: Streamlined the UI by removing redundant CSS, reducing clutter and improving load times for a smoother visual experience.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2\u003e[0.6.11] - 2025-05-27\u003c/h2\u003e\n\u003ch3\u003eAdded\u003c/h3\u003e\n\u003cul\u003e\n\u003cli\u003e🟢 \u003cstrong\u003eOllama Model Status Indicator in Model Selector\u003c/strong\u003e: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.\u003c/li\u003e\n\u003cli\u003e🗑️ \u003cstrong\u003eUnload Ollama Model Directly from Model Selector\u003c/strong\u003e: Easily release memory and resources by unloading any loaded Ollama model right in the model selector—streamline hardware management without switching pages.\u003c/li\u003e\n\u003cli\u003e🗣️ \u003cstrong\u003eUser-Configurable Speech-to-Text Language Setting\u003c/strong\u003e: Improve transcription accuracy by letting individual users explicitly set their preferred STT language in their settings—ideal for multilingual teams and clear audio capture.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGranular Audio Playback Speed Control\u003c/strong\u003e: Instead of just presets, you can now choose granular audio speed using a numeric input, giving you complete control over playback pace in transcriptions and media reviews.\u003c/li\u003e\n\u003cli\u003e📦 \u003cstrong\u003eGZip, Brotli, ZStd Compression Middleware\u003c/strong\u003e: Enjoy significantly faster page loads and reduced bandwidth usage with new server-side compression—giving users a snappier, more efficient experience.\u003c/li\u003e\n\u003cli\u003e🏷️ \u003cstrong\u003eConfigurable Weight for BM25 in Hybrid Search\u003c/strong\u003e: Fine-tune search relevance by adjusting the weight for BM25 inside hybrid search from the UI, letting you tailor knowledge search results to your workflow.\u003c/li\u003e\n\u003cli\u003e🧪 \u003cstrong\u003eBypass File Creation with CTRL + SHIFT + V\u003c/strong\u003e: When “Paste Large Text as File” is enabled, use CTRL + SHIFT + V to skip the file creation dialog and instantly upload text as a file—perfect for rapid document prep.\u003c/li\u003e\n\u003cli\u003e🌐 \u003cstrong\u003eBypass Web Loader in Web Search\u003c/strong\u003e: Choose to bypass web content loading and use snippets directly in web search for faster, more reliable results when page loads are slow or blocked.\u003c/li\u003e\n\u003cli\u003e🚀 \u003cstrong\u003eEnvironment Variable: WEBUI_AUTH_TRUSTED_GROUPS_HEADER\u003c/strong\u003e: Now sync and manage user groups directly via trusted HTTP header, unlocking smoother single sign-on and identity integrations for organizations.\u003c/li\u003e\n\u003cli\u003e🏢 \u003cstrong\u003eWorkspace Models Visibility Controls\u003c/strong\u003e: You can now hide workspace-level models from both the model selector and shared environments—keep your team focused and reduce clutter from rarely-used endpoints.\u003c/li\u003e\n\u003cli\u003e🛡️ \u003cstrong\u003eCopy Model Link\u003c/strong\u003e: You can now copy a direct link to any model—including those hidden from the selector—making sharing and onboarding others more seamless.\u003c/li\u003e\n\u003cli\u003e🔗 \u003cstrong\u003eLoad Function Directly from URL\u003c/strong\u003e: Simplify custom function management—just paste any GitHub function URL into Open WebUI and import new functions in seconds.\u003c/li\u003e\n\u003cli\u003e⚙️ \u003cstrong\u003eCustom Name/Description for External Tool Servers\u003c/strong\u003e: Personalize and clarify external tool servers by assigning custom names and descriptions, making it easier to manage integrations in large-scale workspaces.\u003c/li\u003e\n\u003cli\u003e🌍 \u003cstrong\u003eCustom OpenAPI JSON URL Support for Tool Servers\u003c/strong\u003e: Supports specifying any custom OpenAPI JSON URL, unlocking more flexible integration with any backend for tool calls.\u003c/li\u003e\n\u003cli\u003e📊 \u003cstrong\u003eSource Field Now Displays in Non-Streaming Responses with Attachments\u003c/strong\u003e: When files or knowledge are attached, the \u0026quot;source\u0026quot; field now appears for all responses, even in non-streaming mode—enabling improved citation workflow.\u003c/li\u003e\n\u003cli\u003e🎛 \u003cstrong\u003ePinned Chats\u003c/strong\u003e: Reduced payload size on pinned chat requests—leading to faster load times and less data usage, especially on busy warehouses.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eImport/Export Default Prompt Suggestions\u003c/strong\u003e: Enjoy one-click import/export of prompt suggestions, making it much easier to share, reuse, and manage best practices across teams or deployments.\u003c/li\u003e\n\u003cli\u003e🍰 \u003cstrong\u003eBanners Now Sortable from Admin Settings\u003c/strong\u003e: Quickly re-order or prioritize banners, letting you highlight the most critical info for your team.\u003c/li\u003e\n\u003cli\u003e🛠 \u003cstrong\u003eAdvanced Chat Parameters—Clearer Ollama Support Labels\u003c/strong\u003e: Parameters and advanced settings now explicitly indicate if they are Ollama-specific, reducing confusion and improving setup accuracy.\u003c/li\u003e\n\u003cli\u003e🤏 \u003cstrong\u003eScroll Bar Thumb Improved for Better Visibility\u003c/strong\u003e: Enhanced scrollbar styling makes navigation more accessible and visually intuitive.\u003c/li\u003e\n\u003cli\u003e🗄️ \u003cstrong\u003eModal Redesign for Archived and User Chat Listings\u003c/strong\u003e: Clean, modern modal interface for browsing archived and user-specific chats makes locating conversations faster and more pleasant.\u003c/li\u003e\n\u003cli\u003e📝 \u003cstrong\u003eAdd/Edit Memory Modal UX\u003c/strong\u003e: Memory modals are now larger and have resizable input fields, supporting easier editing of long or complex memory content.\u003c/li\u003e\n\u003cli\u003e🏆 \u003cstrong\u003eTranslation \u0026amp; Localization Enhancements\u003c/strong\u003e: Major upgrades to Chinese (Simplified \u0026amp; Traditional), Korean, Russian, German, Danish, Finnish—not just fixing typos, but consistency, tone, and terminology for a more natural native-language experience.\u003c/li\u003e\n\u003cli\u003e⚡ \u003cstrong\u003eGeneral Backend Stability \u0026amp; Security Enhancements\u003c/strong\u003e: Various backend refinements ensure a more resilient, reliable, and secure platform for smoother operation and peace of mind.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c!-- raw HTML omitted --\u003e\n\u003c/blockquote\u003e\n\u003cp\u003e... (truncated)\u003c/p\u003e\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003eCommits\u003c/summary\u003e\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/ba0088f39b7a093920b142a5172554686f24df60\"\u003e\u003ccode\u003eba0088f\u003c/code\u003e\u003c/a\u003e Merge pull request \u003ca href=\"https://redirect.github.com/open-webui/open-webui/issues/14441\"\u003e#14441\u003c/a\u003e from open-webui/dev\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/661625f3622e006befb79953705ac95dbc8e3ec1\"\u003e\u003ccode\u003e661625f\u003c/code\u003e\u003c/a\u003e doc: changelog\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/30b7ab3591645d13675158423c5f0cd183fb8116\"\u003e\u003ccode\u003e30b7ab3\u003c/code\u003e\u003c/a\u003e refac\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/7dc7d5c028a662c618f09c50e01ccf5b1833a77f\"\u003e\u003ccode\u003e7dc7d5c\u003c/code\u003e\u003c/a\u003e refac: PLEASE FOLLOW EXISTING CONVENTION\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/2c31f5c72540f8cfb9343f1e61885785ee5db310\"\u003e\u003ccode\u003e2c31f5c\u003c/code\u003e\u003c/a\u003e doc: readme\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/a6864db8ece88b9dae743445b290fd03e61e035b\"\u003e\u003ccode\u003ea6864db\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/21f85e63bf26877a62be9a2b6a04b3f4b35b6436\"\u003e\u003ccode\u003e21f85e6\u003c/code\u003e\u003c/a\u003e refac: styling\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/9220afe7b315b53f9afc73756e08d5041c5eedf7\"\u003e\u003ccode\u003e9220afe\u003c/code\u003e\u003c/a\u003e feat: custom advanced params\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/bb4115fa0edbb610f1d3f98c2a02e070579cfdca\"\u003e\u003ccode\u003ebb4115f\u003c/code\u003e\u003c/a\u003e refac: allow all params\u003c/li\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/open-webui/open-webui/commit/551597b9cc09df401ead368f731898052cc6b8cc\"\u003e\u003ccode\u003e551597b\u003c/code\u003e\u003c/a\u003e chore: format\u003c/li\u003e\n\u003cli\u003eAdditional commits viewable in \u003ca href=\"https://github.com/open-webui/open-webui/compare/v0.5.20...v0.6.12\"\u003ecompare view\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/details\u003e\n\u003cbr /\u003e\n\n\n[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=open-webui/open-webui\u0026package-manager=docker\u0026previous-version=v0.5.20\u0026new-version=v0.6.12)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)\n\nDependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.\n\n[//]: # (dependabot-automerge-start)\n[//]: # (dependabot-automerge-end)\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003eDependabot commands and options\u003c/summary\u003e\n\u003cbr /\u003e\n\nYou can trigger Dependabot actions by commenting on this PR:\n- `@dependabot rebase` will rebase this PR\n- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it\n- `@dependabot merge` will merge this PR after your CI passes on it\n- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it\n- `@dependabot cancel merge` will cancel a previously requested merge and block automerging\n- `@dependabot reopen` will reopen this PR if it is closed\n- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually\n- `@dependabot show \u003cdependency name\u003e ignore conditions` will show all of the ignore conditions of the specified dependency\n- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)\n- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)\n\n\n\u003c/details\u003e","html_url":"https://github.com/lucasrod16/self-hosted-llm/pull/64","url":"https://dependabot.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucasrod16%2Fself-hosted-llm/issues/64","packages_url":"https://dependabot.ecosyste.ms/api/v1/issues/64/packages"}}]}