OpenWebUI - Package Updates
-
[2.14.19]
- Update ollama to 0.10.0
-
[2.14.20]
- Update ollama to 0.10.1
-
[2.15.0]
- Update ollama to 0.11.2
-
[2.15.1]
- Update ollama to 0.11.3
-
[2.15.2]
- Update ollama to 0.11.4
-
[2.15.3]
- Update open-webui to 0.6.21
- Full Changelog
- Added display of user groups information in the user edit modal, allowing administrators to view and manage group memberships directly when editing a user.
- Resolved a critical issue where chat completions failed with an "undefined model_id" error after upgrading to version 0.6.20, ensuring all models now function correctly and reliably.
- Fixed an issue where user information was not being correctly logged in the audit trail due to an unreflected function prototype change, ensuring complete logging for administrative oversight.
- Fixed an issue where OpenTelemetry metric and log exporters' 'insecure' settings did not correctly default to the general OpenTelemetry 'insecure' flag, ensuring consistent security configurations across all OpenTelemetry exports.
- Fixed an issue where replying to a message incorrectly displayed '{{INPUT_CONTENT}}' instead of the actual message content, ensuring proper content display in replies.
- Refined and expanded translations for Catalan, Korean, Spanish and Irish, ensuring a more fluent and native experience for global users.
- Fixed a bug where using the "Add" button in Quick Actions would add the resulting message as the very first message in the chat, instead of appending it to the latest message.
- The main navigation sidebar has been completely redesigned with a modern, cleaner aesthetic, featuring a sticky header and footer to keep key controls accessible. Core sidebar logic, like the pinned models list, was also refactored into dedicated components for better performance and maintainability.
- The "Regenerate" button has been transformed into a powerful new menu. You can now guide the AI's next attempt by suggesting changes in a text prompt, or use one-click options like "Try Again," "Add Details," or "More Concise" to instantly refine and reshape the response to better fit your needs.
- Implemented robust handling for tool calls specifically for GPT-OSS models, ensuring proper function execution and integration.
-
[2.15.4]
- Update open-webui to 0.6.22
- Full Changelog
- OpenAI API '/v1' Endpoint Compatibility: 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.
- Toggle for Guided Response Regeneration Menu: 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.
- General UI/UX Enhancements: 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.
- Localization & Internationalization Improvements: Introduced support for the Kabyle (Taqbaylit) language, refined and expanded translations for Chinese, expanding the platform's linguistic coverage.
- OpenAI Error Message Propagation: 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.
- Pinecone Insert Issue: Fixed a bug that prevented proper insertion of items into Pinecone vector databases.
- S3 Vector Issue: Resolved a bug where s3vector functionality failed due to incorrect import paths.
- Landing Page Option Setting Not Working: Fixed an issue where the landing page option in settings was not functioning as intended.
-
[2.16.0]
- Use Redis addon
-
[2.16.1]
- Update ollama to 0.11.5
-
[2.16.2]
- Update ollama to 0.11.6
-
[2.16.3]
- Update open-webui to 0.6.25
- Full Changelog
- Image Generation Reliability Restored: Fixed a key issue causing image generation failures.
- Reranking Functionality Restored: Resolved errors with rerank feature.
- High Contrast Mode in Chat Messages: 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.
- Localization & Internationalization Improvements: Enhanced and expanded translations for a more natural and professional user experience for speakers of these languages across the entire interface.
- ComfyUI Image Generation Restored: 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.
- Tool Server Loading and Visibility Restored: 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.
- Redis User Session Reliability: Fixed a problem affecting the saving of user sessions in Redis, ensuring reliable login sessions, stable authentication, and secure multi-user environments.
- Asynchronous Chat Payload Processing: 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.
- Asynchronous File Upload with Polling: 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.
- Database Performance Indexes and Migration Script: Introduced new database indexes on the "chat", "tag", and "function" 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.
-
[2.16.4]
- Update ollama to 0.11.7
-
[2.16.5]
- Update open-webui to 0.6.26
- Full Changelog
- Granular Chat Interaction Permissions: Added fine-grained permission controls for individual chat actions including "Continue Response", "Regenerate Response", "Rate Response", and "Delete Messages". Administrators can now configure these permissions per user group or set system defaults via environment variables, providing enhanced security and governance by preventing potential system prompt leakage through response continuation and enabling precise control over user interactions with AI responses.
- Custom Reasoning Tags Configuration: Added configurable reasoning tag detection for AI model responses, allowing administrators and users to customize how the system identifies and processes reasoning content. Users can now define custom reasoning tag pairs, use default tags like "think" and "reasoning", or disable reasoning detection entirely through the Advanced Parameters interface, providing enhanced control over AI thought process visibility.
- Pull-to-Refresh SupportA: Added pull-to-refresh functionality allowing user to easily refresh the interface by pulling down on the navbar area. This resolves timeout issues that occurred when temporarily switching away from the app during long AI response generations, eliminating the need to close and relaunch the PWA.
- Configurable File Upload Processing Mode: Added "process_in_background" query parameter to the file upload API endpoint, allowing clients to choose between asynchronous (default) and synchronous file processing. Setting "process_in_background=false" forces the upload request to wait until extraction and embedding complete, returning immediately usable files and simplifying integration for backend API consumers that prefer blocking calls over polling workflows.
- Azure Document Intelligence DefaultAzureCredential Support: Added support for authenticating with Azure Document Intelligence using DefaultAzureCredential in addition to API key authentication, enabling seamless integration with Azure Entra ID and managed identity authentication for enterprise Azure environments.
- Chat Error Feedback Restored: Fixed an issue where various backend errors (tool server failures, API connection issues, malformed responses) would cause chats to load indefinitely without providing user feedback. The system now properly displays error messages when failures occur during chat generation, allowing users to understand issues and retry as needed instead of waiting indefinitely.
- Image Generation Steps Setting Visibility Fixed: Fixed a UI issue where the "Set Steps" configuration option was incorrectly displayed for OpenAI and Gemini image generation engines that don't support this parameter. The setting is now only visible for compatible engines like ComfyUI and Automatic1111, eliminating user confusion about non-functional configuration options.
- Datalab Marker API Document Loader Fixed: Fixed broken Datalab Marker API document loader functionality by correcting URL path handling for both hosted Datalab services and self-hosted Marker servers. Removed hardcoded "/marker" paths from the loader code and restored proper default URL structure, ensuring PDF and document processing works correctly with both deployment types.
- Citation Error Handling Improved: Fixed an issue where malformed citation or source objects from external tools, pipes, or filters would cause JavaScript errors and make the chat interface completely unresponsive. The system now gracefully handles missing or undefined citation properties, allowing conversations to load properly even when tools generate defective citation events.
- Group User Add API Endpoint Fixed: Fixed an issue where the "/api/v1/groups/id/{group_id}/users/add" API endpoint would accept requests without errors but fail to actually add users to groups. The system now properly initializes and deduplicates user ID lists, ensuring users are correctly added to and removed from groups via API calls.
-
[2.16.6]
- Update ollama to 0.11.8
-
[2.16.7]
- Update ollama to 0.11.9
-
[2.16.8]
- Update ollama to 0.11.10
