OpenWebUI - Package Updates
Pinned
OpenWebUI
-
[2.5.9]
- Update Ollama to 0.3.14
-
[2.5.10]
- Update OpenWebUI to 0.3.35
- Full changelog
-
[2.6.0]
- Update ollama to 0.4.0
- Support for Llama 3.2 Vision (i.e. Mllama) architecture
- Sending follow on requests to vision models will now be much faster
- Fixed issues where stop sequences would not be detected correctly
- Ollama can now import models from Safetensors without a Modelfile when running
ollama create my-model - Fixed issue where redirecting output to a file on Windows would cause invalid characters to be written
- Fixed issue where invalid model data would cause Ollama to error
-
[2.6.1]
- Update ollama to 0.4.1
-
[2.6.2]
- Update ollama to 0.4.2
-
[2.7.0]
- Update open-webui to 0.4.0
- Full Changelog
- User Groups: You can now create and manage user groups, making user organization seamless.
- Group-Based Access Control: Set granular access to models, knowledge, prompts, and tools based on user groups, allowing for more controlled and secure environments.
- Group-Based User Permissions: Easily manage workspace permissions. Grant users the ability to upload files, delete, edit, or create temporary chats, as well as define their ability to create models, knowledge, prompts, and tools.
- LDAP Support: Newly introduced LDAP authentication adds robust security and scalability to user management.
- Enhanced OpenAI-Compatible Connections: Added prefix ID support to avoid model ID clashes, with explicit model ID support for APIs lacking '/models' endpoint support, ensuring smooth operation with custom setups.
-
[2.7.1]
- Update open-webui to 0.4.1
- Full Changelog
- Enhanced Feedback System: Introduced a detailed 1-10 rating scale for feedback alongside thumbs up/down, preparing for more precise model fine-tuning and improving feedback quality.
- Tool Descriptions on Hover: Easily access tool descriptions by hovering over the message input, providing a smoother workflow with more context when utilizing tools.
-
[2.7.2]
- Update open-webui to 0.4.2
- Full Changelog
- Knowledge Files Visibility Issue: Resolved the bug preventing individual files in knowledge collections from displaying when referenced with '#'.
- OpenAI Endpoint Prefix: Fixed the issue where certain OpenAI connections that deviate from the official API spec werent working correctly with prefixes.
- Arena Model Access Control: Corrected an issue where arena model access control settings were not being saved.
- Usage Capability Selector: Fixed the broken usage capabilities selector in the model editor.
-
[2.7.3]
- Update ollama to 0.4.3
- Full Changelog
- Tlu 3: Tlu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
- Mistral Large: a new version of Mistral Large with improved Long Context, Function Calling and System Prompt support.
- Fixed crash that occurred on macOS devices with low memory
- Improved performance issues that occurred in Ollama versions 0.4.0-0.4.2
- Fixed issue that would cause
granite3-denseto generate empty responses - Fixed crashes and hanging caused by KV cache management
-
[2.7.4]
- Update open-webui to 0.4.4
- Full Changelog
- Translation Updates: Refreshed Catalan, Brazilian Portuguese, German, and Ukrainian translations, further enhancing the platform's accessibility and improving the experience for international users.
- Mobile Controls Visibility: Resolved an issue where the controls button was not displaying on the new chats page for mobile users, ensuring smoother navigation and functionality on smaller screens.
- RAG Query Generation Issue: Addressed a significant problem where RAG query generation occurred unnecessarily without attached files, drastically improving speed and reducing delays during chat completions.
- Legacy Event Emitter Support: Reintroduced compatibility with legacy "citation" types for event emitters in tools and functions, providing smoother workflows and broader tool support for users.
-
[2.7.5]
- Update ollama to 0.4.4
-
[2.7.6]
- Update ollama to 0.4.5
-
[2.7.7]
- Update open-webui to 0.4.5
- Full Changelog
- ** Model Order/Defaults Reintroduced**: Brought back the ability to set model order and default models, now configurable via Admin Settings > Models > Configure (Gear Icon).
- ** Query Generation Issue**: Resolved an error in web search query generation, enhancing search accuracy and ensuring smoother search workflows.
- ** Textarea Auto Height Bug**: Fixed a layout issue where textarea input height was shifting unpredictably, particularly when editing system prompts.
- ** Ollama Authentication**: Corrected an issue with Ollamas authorization headers, guaranteeing reliable authentication across all endpoints.
- ** Missing Min_P Save**: Resolved an issue where the 'min_p' parameter was not being saved in configurations.
- ** Tools Description**: Fixed a key issue that omitted tool descriptions in tools payload.
-
[2.7.8]
- Update open-webui to 0.4.6
- Full Changelog
- ** Enhanced Translations**: Various language translations improved to make the WebUI more accessible and user-friendly worldwide.
- ** Textarea Shifting Bug**: Resolved the issue where the textarea shifted unexpectedly, ensuring a smoother typing experience.
- ** Model Configuration Modal**: Fixed the issue where the models configuration modal introduced in 0.4.5 wasnt working for some users.
- ** Legacy Query Support**: Restored functionality for custom query generation in RAG when using legacy prompts, ensuring both default and custom templates now work seamlessly.
- ** Improved General Reliability**: Various minor fixes improve platform stability and ensure a smoother overall experience across workflows.
-
[2.7.9]
- Update open-webui to 0.4.7
- Full Changelog
- Prompt Input Auto-Completion: Type a prompt and let AI intelligently suggest and complete your inputs. Simply press 'Tab' or swipe right on mobile to confirm. Available only with Rich Text Input (default setting). Disable via Admin Settings for full control.
- Improved Translations: Enhanced localization for multiple languages, ensuring a more polished and accessible experience for international users.
- Tools Export Issue: Resolved a critical issue where exporting tools wasnt functioning, restoring seamless export capabilities.
- Model ID Registration: Fixed an issue where model IDs werent registering correctly in the model editor, ensuring reliable model setup and tracking.
- Textarea Auto-Expansion: Corrected a bug where textareas didnt expand automatically on certain browsers, improving usability for multi-line inputs.
-
[2.8.0]
- Update ollama to 0.5.1
- Full Changelog
- Fixed issue where Ollama's API would generate JSON output when specifying
"format": null - Fixed issue where passing
--format jsontoollama runwould cause an error - Llama 3.3: a new state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.
- Snowflake Arctic Embed 2: Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
- Fixed error importing model vocabulary files
-
[2.8.1]
- Update open-webui to 0.4.8
- Full Changelog
- Bypass Model Access Control: Introduced the 'BYPASS_MODEL_ACCESS_CONTROL' environment variable. Easily bypass model access controls for user roles when access control isn't required, simplifying workflows for trusted environments.
- Markdown in Banners: Now supports markdown for banners, enabling richer, more visually engaging announcements.
- Internationalization Updates: Enhanced translations across multiple languages, further improving accessibility and global user experience.
- Styling Enhancements: General UI style refinements for a cleaner and more polished interface.
- Rich Text Reliability: Improved the reliability and stability of rich text input across chats for smoother interactions.
- Tailwind Build Issue: Resolved a breaking bug caused by Tailwind, ensuring smoother builds and overall system reliability.
- Knowledge Collection Query Fix: Addressed API endpoint issues with querying knowledge collections, ensuring accurate and reliable information retrieval.
-
[2.8.2]
- Update ollama to 0.5.3
- Full Changelog
- Fixed runtime errors on older Intel Macs
- Fixed issue where setting the
formatfield to""would cause an error - @Askir made their first contribution in https://github.com/ollama/ollama/pull/8028
- EXAONE 3.5: a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
- Fixed issue where whitespace would get trimmed from prompt when images were provided
- Improved memory estimation when scheduling models
-
[2.8.3]
- Update ollama to 0.5.4
- Full Changelog
- Falcon3: A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
- Fixed issue where providing
nulltoformatwould result in an error
