v0.3.2
Tencent/WeKnorav0.3.2Mar 4, 2026by lyingbug
AI Summary
WeKnora v0.3.2 is a feature-rich release introducing major enhancements including Milvus vector database support for knowledge retrieval, async knowledge re-parse API, batch conversation management, and Volcengine TOS cloud storage integration. The release also includes various bug fixes, UI improvements, and refactoring of storage and document processing components.
Key Highlights
- Added Milvus vector database support for knowledge retrieval
- Implemented async knowledge re-parse API with examples
- Added batch management for conversations
- Integrated Volcengine TOS (cloud storage) support
- Added Mermaid diagram display support
Breaking Changes
- Removed mineru_api_base_url from ParserEngineConfig - requires configuration updates for users relying on this setting
- Changed Helm frontend APP_HOST env default value from previous setting to 'app' - may require deployment adjustments
New Features
- Async knowledge re-parse API and examples
- Product roadmap documentation in README files
- Batch management for conversations
- Volcengine TOS cloud storage support
- User level memory graph preview
- Knowledge creation from remote file URLs
- Milvus vectorDB support for knowledge retrieval
- Mermaid display support
- Added TagID and IsRecommended fields to vector embeddings
- Enhanced image handling and UI adjustments in document components
Full Release Notes
## What's Changed * feat: Add async knowledge re-parse API and examples by @begoniezhao in https://github.com/Tencent/WeKnora/pull/679 * feat: add product roadmap documentation and links in README files by @lyingbug in https://github.com/Tencent/WeKnora/pull/685 * fix: handle thinking content in Ollama chat responses by @is-Xiaoen in https://github.com/Tencent/WeKnora/pull/689 * feat(chat): add batch management for conversations by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/692 * feat: add volcengine tos support by @Dounx in https://github.com/Tencent/WeKnora/pull/691 * feat: implement preview of user level memory graph by @chengjoey in https://github.com/Tencent/WeKnora/pull/687 * fix: change helm frontend APP_HOST env default value to app by @ChenRussell in https://github.com/Tencent/WeKnora/pull/694 * fix(auth): update form validation check to handle non-boolean responses by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/695 * feat: Add knowledge creation support from remote file URLs by @begoniezhao in https://github.com/Tencent/WeKnora/pull/696 * feat: support milvus vectordb for knowledge retrieve by @chengjoey in https://github.com/Tencent/WeKnora/pull/699 * fix(swagger): resolve interface documentation generation error and regenerate docs by @ChenRussell in https://github.com/Tencent/WeKnora/pull/698 * Korean update by @andy5090 in https://github.com/Tencent/WeKnora/pull/701 * fix: prevent modal dismiss on text selection & load all sessions in batch manage by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/703 * feat: support mermaid display by @CodeMarker0 in https://github.com/Tencent/WeKnora/pull/702 * Storage & Doc Processor Refactor by @lyingbug in https://github.com/Tencent/WeKnora/pull/704 * feat(repository): add TagID and IsRecommended fields to vector embeddings by @lyingbug in https://github.com/Tencent/WeKnora/pull/705 * refactor: remove mineru_api_base_url from ParserEngineConfig and related components by @lyingbug in https://github.com/Tencent/WeKnora/pull/706 * refactor: simplify image handling in _resolve_images function by @lyingbug in https://github.com/Tencent/WeKnora/pull/709 * feat: enhance image handling and UI adjustments in document components by @lyingbug in https://github.com/Tencent/WeKnora/pull/711 * feat: release v0.3.2 with new features, improvements, and bug fixes by @lyingbug in https://github.com/Tencent/WeKnora/pull/712 ## New Contributors * @is-Xiaoen made their first contribution in https://github.com/Tencent/WeKnora/pull/689 * @andy5090 made their first contribution in https://github.com/Tencent/WeKnora/pull/701 **Full Changelog**: https://github.com/Tencent/WeKnora/compare/v0.3.1...v0.3.2