Importance Notes
- After upgrading, please clear documents and cache, then re-index your documents for document deletion feature functions correctly. Remember to select the "clear cache simultaneously" option when clearing documents. If the document deletion functionality is not immediately required, there is no need to re-index documents.
- This upgrade includes changes to QueryParam parameters. If you previously integrated LightRAG using QueryParam, please update your parameter passing according to the latest API. Refer to the /query endpoint parameters on the web UI's API page.
- The integration of Reranker in this version significantly enhances the performance of mixed queries. We recommend using mixed query mode as the default when Reranker is enabled.
Added
- Add chunk reranking support to improve query performance by @LarFii in #1753 #1782
- Implement document deletion functionality in the WebUI by @danielaskdd in #1698 #1697 #1732
- Implement data isolation for all storage types via WORKSPACE environment variable by @danielaskdd in #1743
- Enable parallel processing in the merge stage of document processing to leverage LLM concurrent capabilities by @maharjun in #1549 #1772 #1771 #1770
- Update ollama compatible api by @SLKun in #1724
- Flatten LLM cache structure for improved recall efficiency by @danielaskdd in #1729
- Webui sync MAX_GRAPH_NODES setting from backend by @danielaskdd in #1747
- Reduce default embedding batch size from 32 to 10 by @danielaskdd in #1750
- Support COT/reasoning model by removing tag for entities and keywords extraction by @SLKun in #1752
- Remove deprecated MAX_TOKEN_SUMMARY parameter to prevent LLM output truncation by @danielaskdd in #1783
- Refine summary logic and add dedicated Ollama num_ctx config by @danielaskdd in #1778
- Add Memgraph as a Supported Graph Database Backend by @DavIvek in #1703 #1766
Fixed
- Remove graspologic pip installation that no longer seems to be used by @pablo-statsig in #1662
- Clean up azure env vars by @a-bruhn in #1654
- Add missing methods for MongoGraphStorage by @kenspirit in #1683
- Fix: Resolving issue with PostgreSQL document chunk KV storage depending on vector storage by @danielaskdd in #1714
- Fix nodes & edges are missing when retrieving knowledge subgraph by @kenspirit in #1704
- Fix GRAPH_FIELD_SEP import typo by @MoDDyChat in #1715
- Fix LLM cache handling for MongoKVStorage to address document deletion scenarios by @danielaskdd in #1718
- Fix LLM cache handling for PGKVStorage to address document deletion scenarios by @danielaskdd in #1717
- Fix LLM cache handling for Redis(Reverted) by @danielaskdd in #1719
- Refac: Add KG rebuild logging with pipeline status by @danielaskdd in #1720
- Feat: Check pending equest_pending after document deletion by @danielaskdd in #1735
- Refactoring implementation of Milvus vector storage by @danielaskdd in #1736
- fix: prevent empty entity names after normalization in extraction by @danielaskdd in #1737
- Fix: Resolve the issue of blank content in PDF extractions @okxuewei in #1738
- Fix incorrect file path (404 Not Found) by @frankxjkuang in #1749
- Fix: Ensured token tracking information is present for stream responses from OpenAI by @danielaskdd in #1757
- Fix #1746: [openai.py logic for streaming complete] by @molion097 in #1751
- Fix: Handle NoneType error when processing documents without a file path by @antonvice in #1759
- fix(build): pyproject.toml setup by @schmidt-marvin in #1768
- Feat: Added reranker config and lock status to status card of WebUI by @danielaskdd in #1773
- Hotfix: prevent premature lock cleanup in multiprocess mode by @danielaskdd in #1774
- Hotfix: Resolves connection pool bugs for Redis by @danielaskdd in #1775
- Increase max length limits for Milvus storage fields by @danielaskdd in #1776
- Increase field lengths for entity and file paths for PostgreSQL by @danielaskdd in #1777
- Fix: Resolve timezone handling problem in PostgreSQL storage by @danielaskdd in #1779
- Add Cloudflare Workers AI support for serverless LLM/embedding by @al1kss in #1765
New Contributors
- @kenspirit made their first contribution in #1683
- @pablo-statsig made their first contribution in #1662
- @a-bruhn made their first contribution in #1654
- @MoDDyChat made their first contribution in #1715
- @SLKun made their first contribution in #1724
- @okxuewei made their first contribution in #1738
- @frankxjkuang made their first contribution in #1749
- @molion097 made their first contribution in #1751
- @DavIvek made their first contribution in #1703
- @antonvice made their first contribution in #1759
- @schmidt-marvin made their first contribution in #1768
- @al1kss made their first contribution in #1765
Full Changelog: v1.3.9...v1.4.0