v0.3.6
Tencent/WeKnorav0.3.6Apr 3, 2026by lyingbug
AI Summary
Release focused on provider additions, IM features, security improvements, and audio/video processing capabilities.
Key Highlights
- OIDC authentication
- Parallel tool calling support
- Tavily web search provider
- Thread-based IM sessions
- ASR (speech-to-text) model support
New Features
- OIDC authentication
- Parallel tool calling
- Tavily search
- Thread-based IM
- ASR support
- Audio file preview
- Mermaid rendering fix
- Ollama web search
- Baidu web search
Full Release Notes
## What's Changed
* perf(frontend): optimize login page rendering performance by @aahowe in https://github.com/Tencent/WeKnora/pull/824
* fix: update doc-content.vue renderer to marked v5+ token API by @ochanism in https://github.com/Tencent/WeKnora/pull/829
* refactor: use unified NVIDIA API for both chat and VLM by @manx98 in https://github.com/Tencent/WeKnora/pull/838
* feat: support parallel tool calling by @renezander030 in https://github.com/Tencent/WeKnora/pull/835
* feat: fix enable_thinking for Aliyun Qwen models in streaming mode by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/832
* feat(im): add thread-based session mode for IM channels by @ochanism in https://github.com/Tencent/WeKnora/pull/831
* feat: support system proxy for remote API by @manx98 in https://github.com/Tencent/WeKnora/pull/836
* fix(frontend): resolve mermaid not rendering on page refresh by @manx98 in https://github.com/Tencent/WeKnora/pull/834
* fix(storage): add S3 provider scheme support to frontend and backend allowlists by @ochanism in https://github.com/Tencent/WeKnora/pull/845
* feat(knowledge): resolve remote images in file upload path by @ochanism in https://github.com/Tencent/WeKnora/pull/843
* feat: Authentication with OIDC by @Windfarer in https://github.com/Tencent/WeKnora/pull/833
* feat(datasource): add datasource management, Feishu sync, and ownership enforcement by @lyingbug in https://github.com/Tencent/WeKnora/pull/846
* feat: update readme & docs by @lyingbug in https://github.com/Tencent/WeKnora/pull/847
* chore: update architecture diagram by @lyingbug in https://github.com/Tencent/WeKnora/pull/848
* feat(database): enhance DatabaseQueryTool with search scope filtering by @lyingbug in https://github.com/Tencent/WeKnora/pull/850
* feat(mcp): implement reconnection logic for MCP tool calls and tool listing by @lyingbug in https://github.com/Tencent/WeKnora/pull/851
* refactor(chat): simplify temperature option handling in chat request builders (#793) by @lyingbug in https://github.com/Tencent/WeKnora/pull/852
* feat: add Tavily as configurable web search provider by @tavily-integrations in https://github.com/Tencent/WeKnora/pull/849
* feat(web-search): refactor web search provider by @lyingbug in https://github.com/Tencent/WeKnora/pull/858
* fix(security): support IPv6 in SSRF validation via whitelist mechanism by @voidkey in https://github.com/Tencent/WeKnora/pull/856
* fix(knowledge): allow deselecting document category by clicking again by @voidkey in https://github.com/Tencent/WeKnora/pull/855
* fix(web_fetch): use ValidateURLForSSRF instead of removed IsSSRFSafeURL by @voidkey in https://github.com/Tencent/WeKnora/pull/859
* fix: docreader add monkey patch for docx parse error by @Windfarer in https://github.com/Tencent/WeKnora/pull/862
* feat(chunker): implement header tracking for Markdown tables during chunking by @lyingbug in https://github.com/Tencent/WeKnora/pull/863
* feat(metadata): enhance document processing to include metadata extraction and handling by @lyingbug in https://github.com/Tencent/WeKnora/pull/866
* fix(elasticsearch): restore ".keyword" suffix for Terms queries on ID fields by @ochanism in https://github.com/Tencent/WeKnora/pull/874
* fix(frontend): use storage_provider_config instead of legacy storage_config by @ochanism in https://github.com/Tencent/WeKnora/pull/869
* fix(auth): simplify oidc callback result payload by @Windfarer in https://github.com/Tencent/WeKnora/pull/871
* refactor(prompt_templates): improve question generation guidelines and context handling by @lyingbug in https://github.com/Tencent/WeKnora/pull/877
* feat(knowledge): enhance knowledge tag batch update with authorization checks by @lyingbug in https://github.com/Tencent/WeKnora/pull/878
* feat(docreader): add docx max pages env config by @Windfarer in https://github.com/Tencent/WeKnora/pull/884
* docs: reorder Web UI table rows and remove outdated MCP server setup instructions by @lyingbug in https://github.com/Tencent/WeKnora/pull/885
* docs: update project descriptions and features in multiple language READMEs by @lyingbug in https://github.com/Tencent/WeKnora/pull/886
* docs: update README files to streamline section headings and remove redundant content across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/888
* fix(i18n): use WEKNORA_LANGUAGE env for prompt language fallback instead of hardcoded zh-CN by @ochanism in https://github.com/Tencent/WeKnora/pull/876
* fix(knowledge): delete extracted images from storage when knowledge is removed by @ochanism in https://github.com/Tencent/WeKnora/pull/880
* feat(elasticsearch): enhance ID field handling with dynamic suffix detection by @lyingbug in https://github.com/Tencent/WeKnora/pull/889
* fix(frontend): add null checks for markdown code block text parameter by @ChenRussell in https://github.com/Tencent/WeKnora/pull/891
* feat(summary): enhance document summarization capabilities and UI by @lyingbug in https://github.com/Tencent/WeKnora/pull/892
* fix(stream): use io.EOF instead of errors.New("EOF") in SSEReader by @voidkey in https://github.com/Tencent/WeKnora/pull/893
* feat(asr): support asr model and audio parser by @lyingbug in https://github.com/Tencent/WeKnora/pull/894
* feat(chat): refine parent-child chunk replacement logic in merge process by @lyingbug in https://github.com/Tencent/WeKnora/pull/895
* fix(migrations): correct migration numbers and remove broken trigger by @ChenRussell in https://github.com/Tencent/WeKnora/pull/898
* Feat/im quote reply context by @voidkey in https://github.com/Tencent/WeKnora/pull/883
* feat(audio): add audio file preview support and enhance UI components by @lyingbug in https://github.com/Tencent/WeKnora/pull/899
* chore(release): update to version 0.3.6 by @lyingbug in https://github.com/Tencent/WeKnora/pull/900
## New Contributors
* @renezander030 made their first contribution in https://github.com/Tencent/WeKnora/pull/835
* @Windfarer made their first contribution in https://github.com/Tencent/WeKnora/pull/833
* @tavily-integrations made their first contribution in https://github.com/Tencent/WeKnora/pull/849
**Full Changelog**: https://github.com/Tencent/WeKnora/compare/v0.3.5...v0.3.6