Skip to content

Releases: ITV/open-webui

v0.8.10

09 Mar 10:00
e4e69a1

Choose a tag to compare

Added

  • 🔐 Custom OIDC logout endpoint. Administrators can now configure a custom OpenID Connect logout URL via OPENID_END_SESSION_ENDPOINT, enabling logout functionality for OIDC providers that require custom endpoints like AWS Cognito. Commit
  • 🗄️ MariaDB Vector community support. Added MariaDB Vector as a new vector database backend, enabling deployments with VECTOR_DB=mariadb-vector; supports cosine and euclidean distance strategies with configurable HNSW indexing. #21931
  • 📝 Task message truncation. Chat messages sent to task models for title and tag generation can now be truncated using a filter in the prompt template, reducing token usage and processing time for long conversations. #21499
  • 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability, and security.
  • 🌐 Translations for Portuguese (Brazil), Spanish, and Malay were enhanced and expanded.

Fixed

  • 🔗 Pipeline filter HTTP errors. Fixed a bug where HTTP errors in pipeline inlet/outlet filters would silently corrupt the user's chat payload; errors are now properly raised before parsing the response. #22445
  • 📚 Knowledge file embedding updates. Fixed a bug where updating knowledge files left old embeddings in the database, causing search results to include duplicate and stale data. #20558
  • 📁 Files list stability. Fixed the files list ordering to use created_at with id as secondary sort, ensuring consistent ordering and preventing page crashes when managing many files. #21879
  • 📨 Teams webhook crash. Fixed a TypeError crash in the Teams webhook handler when user data is missing from the event payload. #22444
  • 🛠️ Process shutdown handling. Fixed bare except clauses in the main process that prevented clean shutdown; replaced with proper exception handling. #22423
  • 🐳 Docker deployment startup. Docker deployments now start correctly; the missing OpenTelemetry system metrics dependency was added. #22447, #22401
  • 🛠️ Tool access for non-admin users. Fixed a NameError that prevented non-admin users from viewing tools; the missing has_access function is now properly imported. #22393
  • 🔐 OAuth error handling. Fixed a bug where bare except clauses silently caught SystemExit and KeyboardInterrupt, preventing clean process shutdown during OAuth authentication. #22420
  • 🛠️ Exception error messages. Fixed three locations where incorrect exception raising caused confusing TypeError messages instead of proper error descriptions, making debugging much easier. #22446
  • 📄 YAML file processing. Fixed an error when uploading YAML files with Docling enabled; YAML and YML files are now properly recognized as text files and processed correctly. #22399, #22263
  • 📅 Time range month names. Fixed month names in time range labels appearing in the wrong language when OS regional settings differ from browser language; month names now consistently display in English. #22454
  • 🔐 OAuth error URL encoding. Fixed OAuth error messages with special characters causing malformed redirect URLs; error messages are now properly URL-encoded. #22415
  • 🛠️ Internal tool method filtering. Tools no longer expose internal methods starting with underscore to the LLM, reducing clutter and improving accuracy. #22408
  • 🔊 Azure TTS locale extraction. Fixed Azure text-to-speech using incomplete locale codes in SSML; now correctly uses full locale like "en-US" instead of just "en". #22443
  • 🎤 Azure speech transcription errors. Improved Azure AI Speech error handling to display user-friendly messages instead of generic connection errors; empty transcripts, no language identified, and other Azure-specific errors now show clear descriptions. #20485
  • 📊 Analytics group filtering. Fixed token usage analytics not being filtered by user group; the query now properly respects group filters like other analytics metrics. #22167
  • 🔍 Web search favicon fallback. Fixed web search sources showing broken image icons when favicons couldn't be loaded from external sources; now falls back to the default Open WebUI favicon. #21897
  • 🔄 Custom model fallback. Fixed custom model fallback not working when the base model is unavailable; the base model ID is now correctly retrieved from model info instead of empty params. #22456
  • 🖼️ Pending message image display. Fixed images in queued messages appearing blank; image thumbnails are now properly displayed in the pending message queue. #22256
  • 🛠️ File metadata sanitization. Fixed file uploads failing with JSON serialization errors when metadata contained non-serializable objects like callable functions; metadata is now sanitized before database insertion. #20561

v0.6.36

10 Nov 11:11
e0d5de1

Choose a tag to compare

[0.6.36] - 2025-11-07

Added

  • 🔐 OAuth group parsing now supports configurable separators via the "OAUTH_GROUPS_SEPARATOR" environment variable, enabling proper handling of semicolon-separated group claims from providers like CILogon. #18987, #18979

Fixed

  • 🛠️ Tool calling functionality is restored by correcting asynchronous function handling in tool parameter updates. #18981
  • 🖼️ The ComfyUI image edit workflow editor modal now opens correctly when clicking the Edit button. #18978
  • 🔥 Firecrawl import errors are resolved by implementing lazy loading and using the correct class name. #18973
  • 🔌 Socket.IO CORS warning is resolved by properly configuring CORS origins for Socket.IO connections. Commit

v0.6.34

21 Oct 06:55
7a83e7d

Choose a tag to compare

[0.6.34] - 2025-10-16

Added

  • 📄 MinerU is now supported as a document parser backend, with support for both local and managed API deployments. #18306
  • 🔒 JWT token expiration default is now set to 4 weeks instead of never expiring, with security warnings displayed in backend logs and admin UI when set to unlimited. #18261, #18262
  • ⚡ Page loading performance is improved by preventing unnecessary API requests when sidebar folders are not expanded. #18179, #17476
  • 📁 File hash values are now included in the knowledge endpoint response, enabling efficient file synchronization through hash comparison. #18284, #18283
  • 🎨 Chat dialog scrollbar visibility is improved by increasing its width, making it easier to use for navigation. #18369, #11782
  • 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
  • 🌐 Translations for Catalan, Chinese, Czech, Finnish, German, Kabyle, Korean, Portuguese (Brazil), Spanish, Thai, and Turkish were enhanced and expanded.

Fixed

  • 📚 Focused retrieval mode now works correctly, preventing the system from forcing full context mode and loading all documents in a knowledge base regardless of settings. #18133
  • 🔧 Filter inlet functions now correctly execute on tool call continuations, ensuring parameter persistence throughout tool interactions. #18222
  • 🛠️ External tool servers now properly support DELETE requests with body data. #18289, #18287
  • 🗄️ Oracle23ai vector database client now correctly handles variable initialization, resolving UnboundLocalError when retrieving items from collections. #18356
  • 🔧 Model auto-pull functionality now works correctly even when user settings remain unmodified. #18324
  • 🎨 Duplicate HTML content in artifacts is now prevented by improving code block detection logic. #18195, #6154
  • 💬 Pinned chats now appear in the Reference Chats list and can be referenced in conversations. #18288
  • 📝 Misleading knowledge base warning text in documents settings is clarified to correctly instruct users about reindexing vectors. #18263
  • 🔔 Toast notifications can now be dismissed even when a modal is open. #18260
  • 🔘 The "Chats" button in the sidebar now correctly toggles chat list visibility without navigating away from the current page. #18232
  • 🎯 The Integrations menu no longer closes prematurely when clicking outside the Valves modal. #18310
  • 🛠️ Tool ID display issues where "undefined" was incorrectly shown in the interface are now resolved. #18178
  • 🛠️ Model management issues caused by excessively long model IDs are now prevented through validation that limits model IDs to 256 characters. #18125