v1.4.9.11
Breaking Changes
None
Features
- Vertex AI support for Gemini LLM binding — use Google's Vertex AI as LLM backend
- Gemini migrated to native async Google GenAI client — replaces previous implementation
- MDX file type support — add
.mdxto supported document formats - i18n localization — Korean, German, Ukrainian, Russian, Japanese added
- WebUI token auto-renewal — sliding window expiration for session management
Fixes
- OpenAI LLM binding now reads env variables — options previously ignored from environment
- DOCX extraction now uses HTML tags for whitespace — improved parsing accuracy
- PostgreSQL reconnection tolerance for HA deployments — better fault handling
- Documentation updates (README examples, Gemini integration, demo scripts with PostgreSQL/vLLM)
Hot Fixed
- Fix OpenAI LLM binding options not loaded from environment variables by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2585
What's New
-
feat(gemini): Add Vertex AI support for Gemini LLM binding by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2529
-
refact(gemini): Migrate Gemini LLM to native async Google GenAI client by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2531
-
Refact: Change DOCX extraction to use HTML tags for whitespace by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2550
-
feat: add Korean localization by @jhchoi1182 in https://github.com/HKUDS/LightRAG/pull/2571
-
Add support for mdx file type by @coldfire-x in https://github.com/HKUDS/LightRAG/pull/2566
-
Add i18n support for German, Ukrainian, Russian, and Japanese languages by @mlimarenko in https://github.com/HKUDS/LightRAG/pull/2547
What's Fixed
- docs: fix the simple program rag init function return value in README.md by @Peefy in https://github.com/HKUDS/LightRAG/pull/2532
- docs: fix the simple program rag init function return value in README-zh.md by @Peefy in https://github.com/HKUDS/LightRAG/pull/2534
- feat: Implement WebUI Token Auto-Renewal (Sliding Window Expiration) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2543
- Fixes the Gemini integration example in the README by @vishvaRam in https://github.com/HKUDS/LightRAG/pull/2537
- Add Gemini demo for LightRAG by @vishvaRam in https://github.com/HKUDS/LightRAG/pull/2538
- Add LightRAG demo with PostgreSQL and Gemini integration by @vishvaRam in https://github.com/HKUDS/LightRAG/pull/2556
- Update PostgreSQL demo script reference in README.md by @vishvaRam in https://github.com/HKUDS/LightRAG/pull/2557
- Fix: Enhance PostgreSQL Reconnection Tolerance for HA Deployments by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2562
- Add NEO4J_DATABASE variable to README by @vishvaRam in https://github.com/HKUDS/LightRAG/pull/2578
- Bump the frontend-minor-patch group in /lightrag_webui with 2 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/2577
- Add LightRAG demo script with vLLM integration by @vishvaRam in https://github.com/HKUDS/LightRAG/pull/2582
New Contributors
- @Peefy made their first contribution in https://github.com/HKUDS/LightRAG/pull/2532
- @vishvaRam made their first contribution in https://github.com/HKUDS/LightRAG/pull/2537
- @mlimarenko made their first contribution in https://github.com/HKUDS/LightRAG/pull/2547
- @jhchoi1182 made their first contribution in https://github.com/HKUDS/LightRAG/pull/2571
- @coldfire-x made their first contribution in https://github.com/HKUDS/LightRAG/pull/2566
Full Changelog: https://github.com/HKUDS/LightRAG/compare/v1.4.9.10...v1.4.9.11