Releases: HKUDS/LightRAG
Releases · HKUDS/LightRAG
v1.4.6
What's New
- feat(performance): Optimize Document Deletion Performance with Entity/Relation Indexing by @danielaskdd in #1904
- refactor: improve JSON parsing reliability with json-repair library by @danielaskdd in #1897
What's Fixed
- Fix: resolved workspace isolation problem for json KV storage by @danielaskdd in #1899
- Fix: move OllamaServerInfos class to base module by @danielaskdd in #1893
- Add graceful shutdown handling for LightRAG server by @danielaskdd in #1895
Full Changelog: v1.4.5...v1.4.6
Contributors
danielaskdd
Assets 2
v1.4.5
What's New
- Feat(webui): add document list pagination for webui by @danielaskdd in #1886
- Feat: add Document Processing Track ID Support for Frontend by @danielaskdd in #1882
- Better prompt for entity description extraction to avoid hallucinations by @AkosLukacs in #1845
- Refine entity continuation prompt to avoid duplicates and reducing document processing time by @danielaskdd in #1868
- feat: Add rerank score filtering with configurable threshold by @danielaskdd in #1871
- Feat(webui): add query param reset buttons to webui by @danielaskdd in #1889
- Feat(webui): enhance status card with new settings from health endpoint by @danielaskdd in #1873
What's Fixed
- fix(webui): Correct edge renderer for sigma.js v3 by @danielaskdd in #1863
- Fix: file_path exceeds max length by @okxuewei in #1862
- refactor: unify file_path handling across merge and rebuild functions by @danielaskdd in #1869
- Fix: Improve keyword extraction prompt for robust JSON output. by @danielaskdd in #1872
- allow options to be passed to ollama client when using ollama binding [improved] by @michele-comitini in #1874
- refactor: Remove deprecated
max_token_sizefrom embedding configura… by @danielaskdd in #1875 - Fix: corrected unterminated f-string in config.py by @Ja1aia in #1876
- feat: add processing time tracking to document status with metadata field by @danielaskdd in #1883
- fix timeout issue by @Ja1aia in #1878
- fix: Add safe handling for missing file_path in PostgreSQL by @danielaskdd in #1891
- Remove content in doc status to improve performance by @danielaskdd in #1881
New Contributors
- @michele-comitini made their first contribution in #1874
- @Ja1aia made their first contribution in #1876
Full Changelog: v1.4.4...v1.4.5
Contributors
AkosLukacs, michele-comitini, and 3 other contributors
Assets 2
v1.4.4
New
- Refac: optimizing context builder to improve query performance by @danielaskdd in #1848
- Improve query for find_text_unit by @okxuewei in #1812
- feat: Integrate Jina embeddings API support by @danielaskdd in #1851
- feat: Add SSL support for PostgreSQL database connections by @danielaskdd in #1834
- Fix: rename rerank parameter from top_k to top_n by @danielaskdd in #1815
Fixed
- fix(postgres): handle ssl_mode="allow" in _create_ssl_context by @danielaskdd in #1852
- Fix "A Simple Program" example in README.md by @AkosLukacs in #1844
- Feat: add PostgreSQL extensions for vector and AGE by @danielaskdd in #1833
New Contributors
- @AkosLukacs made their first contribution in #1844
Full Changelog: v1.4.3...v1.4.4
Contributors
AkosLukacs, danielaskdd, and okxuewei
Assets 2
v1.4.3
New
- Feat: change default query mode from hybrid to mix by @danielaskdd in #1797
- Add Azure deployment by @Chida82 in #1801
- Remove separate requirements.txt and update Dockerfile to use pip install by @danielaskdd in #1799
Fixed
- Fix: resolved PostgreSQL AGE agtype parsing error and simplify error logging by @danielaskdd in #1802
- Fix: implemented entity-keyed locks for edge merging operations to ensure robust race condition protection by @danielaskdd in #1811
- Fix: add retry mechanism for Memgraph transient errors by @danielaskdd in #1810
- Fix file path handling in graph operations by @danielaskdd in #1796
- Enhance Redis connection handling with retries and timeouts by @danielaskdd in #1809
New Contributors
Full Changelog: v1.4.2...v1.4.3
Contributors
Chida82 and danielaskdd
Assets 2
v1.4.2
Hotfix: Resolve entity_type and weight problem for Milvus DB
- Fix Milvus DataNotMatchException by @okxuewei in #1792
- fix: change default edge weight from 0.0 to 1.0 in entity extraction and graph storage by @danielaskdd in #1794
Full Changelog: v1.4.1...v1.4.2
Contributors
danielaskdd and okxuewei
Assets 2
v1.4.1
Hotfix: Resolved PostgreSQL data migration problem for v1.4.0
- Optimize PostgreSQL database migrations speed for LLM cache
- Fix LLM cache key translation error for PostgreSQL
- Fix PostgreSQL AGE graph storage workspace error after migration
- Fix timezone problem for document list.
Other fixed
- Remove max token summary display from splash screen
- Update i18n translation for new query parameters
- Limit file deletion to current directory only after document cleaning
Full Changelog: v1.4.0...v1.4.1
v1.4.0
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
Contributors
kenspirit, maharjun, and 13 other contributors
Assets 2
v1.3.9
What's Changed
- docs: Add clear initialization requirements and troubleshooting section by @neno-is-ooo in #1665
- Add doc for explaining LightRAG's multi-document concurrent processing mechanism by @earayu in #1619
- feat: Support
application/octet-streamrequests from LiteLLM clients for Ollama Emulation by @danielaskdd in #1673 - Feat: RAG-Anything Integration by @LarFii in #1688
- Feat: Add comprehensive document deletion feature with integrated knowledge graph reconstruction by @LarFii in #1693
Bugs fixed
- fix typo: "extrat" -> extract by @kwilt in #1667
- Fix: Increase Ollama timeout values to prevent ReadTimeout errors by @eddiemaru-101 in #1643
- Fix incorrect spacing by @Chaoyingz in #1671
New Contributors
- @neno-is-ooo made their first contribution in #1665
- @kwilt made their first contribution in #1667
- @eddiemaru-101 made their first contribution in #1643
- @Chaoyingz made their first contribution in #1671
Full Changelog: v1.3.8...v1.3.9
Contributors
earayu, Chaoyingz, and 5 other contributors
Assets 2
v1.3.8
What's Changed
- Fix: Correct GraphML to JSON mapping in xml_to_json function by @sa9arr in #1592
- Fix js files MIME type error for Windows environment by @danielaskdd in #1605
- Reflect core library parameter update in API server by @yumpyy in #1607
- Adding file_source.s as optional attribute to text.s requests by @belabon25 in #1608
- feat: Integrate Opik for Enhanced Observability in LlamaIndex LLM Int… by @MartinPerez in #1604
- Add Kubernetes Helm Chart for LightRAG Deployment by @earayu in #1602
- Adding citation support in custom graph creation by @omriAl in #1633
- feat: add LaTeX formula rendering support to ChatMessage component by @danielaskdd in #1647
- MinerU integration by @LarFii in #1659
New Contributors
- @sa9arr made their first contribution in #1592
- @yumpyy made their first contribution in #1607
- @belabon25 made their first contribution in #1608
- @MartinPerez made their first contribution in #1604
- @omriAl made their first contribution in #1633
Full Changelog: v1.3.7...v1.3.8
Contributors
MartinPerez, earayu, and 6 other contributors
Assets 2
v1.3.7
What's New
- Feat: Add user prompt to QueryParam by @danielaskdd in #1546 #1552
- Deduplicate merged relation keywords by @danielaskdd in #1550
- Allow max_connections to be configured in postgres by @maharjun in #1547
- Persistent LLM cache on error by @danielaskdd in #1511
- Use Openai Client Context Manager by @maharjun in #1548
- Adding Tongyi OpenAI demo to use Qwen model by @geekben in #1518
- Made bedrock_complete generic by @balaji-munusamy in #1508
- Optimize query context format for mix and naive mode query by @danielaskdd in #1545
- Update Dockerfile and docker-compose.yml by @danielaskdd in #1570
- Update ollama LLM driver and sample code by @danielaskdd in #1572
Bugs fixed
- Fix node names with JSON formatting were mistakenly interpreted as JSON objects for PostgreSQL AGE graph storage by @danielaskdd in #1512
- Fix JSON handling error for PostgreSQL graph storage by @danielaskdd in #1519
- Update postgres_impl.py syntax to create tables section by @widgit in #1524
- Fix time zone and created_at problem by @danielaskdd in #1510
- Eliminate redundant chunk data fetching in naive and mix query mode by @danielaskdd in #1537
- Ignore chat history in vector search by @danielaskdd in #1538
- Fix streaming problem for OpenAI by @danielaskdd in #1553
- Resolve json code block freezing issue in WebUI by @danielaskdd in #1539
- security fix by @venkateshpabbati in #1325
New Contributors
- @balaji-munusamy made their first contribution in #1508
- @geekben made their first contribution in #1518
- @maharjun made their first contribution in #1547
- @venkateshpabbati made their first contribution in #1325
Full Changelog: v1.3.6...v1.3.7
Contributors
maharjun, geekben, and 4 other contributors