v1.1.4

What's Changed

• Fixed API docs link in Readme.md by @nickjfrench in #617
• Addind a simple tool to view the lightrag database in 3d by @ParisNeo in #622
• Replacing ParisNeo with this repo owner, HKUDS by @nickjfrench in #618
• feat: Added Redis KV storage, OpenAI+Neo4j+Milvus+Redis demo tests, and added lightRAG.py: R… by @18277486571HYB in #616
• Fix: docker build by @soichisumi in #624
• Fix parms missing for openai by @danielaskdd in #628
• add "azure_openai" in llm_binding and embedding_binding by @soichisumi in #630
• Fixed bug that caused data update to freeze when an exception occurred by @magicyuan876 in #634
• feat: Added INI file reading for database configuration, making it easier for production environments, modified LightRAG's ainsert method _add_doc... by @18277486571HYB in #631
• fix completion_delimiter with record_delimiter, by @RayWang1991 in #637
• Support multi-turn conversations by @magicyuan876 in #639
• Upgraded docstrings for lightrag-server.py And added a simple front end to interact with the AI by @ParisNeo in #640
• Fixed workspace matching in oracle_impl.py by @da-luggas in #641
• asyncio optimizations by @dimatill in #642
• Add ollama generate api support by @danielaskdd in #644
• Major Refactoring: LLM Components, UI Updates, and Dependency Management by @ParisNeo in #645

New Contributors

• @18277486571HYB made their first contribution in #616
• @soichisumi made their first contribution in #624
• @RayWang1991 made their first contribution in #637
• @da-luggas made their first contribution in #641
• @dimatill made their first contribution in #642

Full Changelog: v1.1.3...v1.1.4

v1.1.3

What's Changed

• Major Updates: Docker Support, Enhanced Configuration, and Documentation Restructuring #554 by @ParisNeo in #593
• add readme_zh by @luohuanhuan2019 in #591
• Add Ollama compatible API server by @danielaskdd in #592
• Fixes #596 - Hardcoded model deployment name in azure_openai_complete by @nickjfrench in #597
• Migrate Ollama emulation features from lightrag_ollama to lightrag_server by @danielaskdd in #600
• Use LLM_MODEL env var in Azure OpenAI function by @danielaskdd in #602
• Pull Request: API Key Management Implementation and Azure OpenAI Bug Fix by @ParisNeo in #605
• Update OpenAI alike LLM API key handling in lightrag_server by @danielaskdd in #607
• Temporary fix to introduced problem in ollama and lollm by @ParisNeo in #608
• Add document indexing during FastAPI startup, Fix docx package name i… by @danielaskdd in #610
• Added OpenWebui Tool by @ParisNeo in #613

New Contributors

• @luohuanhuan2019 made their first contribution in #591
• @danielaskdd made their first contribution in #592
• @nickjfrench made their first contribution in #597

Full Changelog: v1.1.2...v1.1.3

v1.1.2

What's Changed

• Fix for mongoDB document 16MB limit and add os env NEO4J_MAX_CONNECTION_POOL_SIZE for neo4j by @jiabin2wang20230918 in #581
• Enhancement: Multi-format document support and dynamic dependency management #565 by @ParisNeo in #587
• Enrich README.md for postgres usage, fix the issue for running postgres on python version<12 by @ShanGor in #589
• Add custom function with separate keyword extraction for user's query and a separate prompt by @gurjot-05 in #585
• Enhance Robustness of insert Method with Pipeline Processing and Caching Mechanisms by @jin38324 in #590

New Contributors

• @jiabin2wang20230918 made their first contribution in #581
• @gurjot-05 made their first contribution in #585

Full Changelog: v1.1.1...v1.1.2

v1.1.1

What's Changed

• Add character segmentation functionality for chunks by @tongshiyuan in #551
• Fix:Optimized logic for automatic switching modes when keywords do not exist by @n3A87 in #547
• Implement custom chunking feature by @GurjotSinghShorthillsAI in #553
• Restore backwards compatibility for LightRAG's ainsert method by @ParisNeo in #555
• Optimize the character segmentation parameters by @tongshiyuan in #557
• Add custom chunking function. by @AdiKalra in #560
• [API Enhancement] Consolidate API Servers and Add HTTPS Support (#565) by @ParisNeo in #569
• Revise the AGE usage for postgres_impl by @ShanGor in #570
• Highlight the Apache AGE release version issue in the README.MD by @ShanGor in #573
• fix: Resolve 500 error caused by missing len() for LightRAG by @iridium-soda in #572
• Fix 500 error in LightRAG's API insert_text endpoint by @ParisNeo in #575
• Revise the AGE implementation on get_node_edges, to align with Neo4j behavior. by @ShanGor in #576

New Contributors

• @tongshiyuan made their first contribution in #551
• @n3A87 made their first contribution in #547
• @GurjotSinghShorthillsAI made their first contribution in #553
• @AdiKalra made their first contribution in #560
• @iridium-soda made their first contribution in #572

Full Changelog: v1.1.0...v1.1.1

v1.1.0

What's Changed

• Add Optional API Key Authentication to FastAPI Services by @ParisNeo in #541
• Added PostgreSQL implementation by @ShanGor in #539
• Add support for selecting a specific database in Neo4j by @xiyihan0 in #542
• Enhance the llm_cache_kv_store, enable the llm_cache for entity extraction and revise readme by @ShanGor in #545

New Contributors

• @xiyihan0 made their first contribution in #542

Full Changelog: v1.0.9...v1.1.0

v1.0.9

What's Changed

• Streamlined API Installation and Documentation Enhancement by @ParisNeo in #514
• Fixed keywords_extraction_examples format error by @zhangch-ss in #515
• Fixed the async issue while running on Windows by @ShanGor in #516
• Feature (lightrag): Added document status tracking and breakpoint resume support by @magicyuan876 in #521
• Feature (lightrag): Implemented mixed search mode combining knowledge graph and other techniques by @magicyuan876 in #523
• Optimized the prompts in the mixed search mode by @magicyuan876 in #524
• Feature: Enhanced temporal support for knowledge graph relationships by @magicyuan876 in #525
• Fixed breakpoint resume bug, ensuring that only documents with completed statuses are filtered out by @magicyuan876 in #529
• Fixed: Changed exception type by @ChenZiHong-Gavin in #527
• Development updates by @LarFii in #532
• Updated LICENSE, fixed copyright license year by @JasonnnW3000 in #533

New Contributors

• @zhangch-ss made their first contribution in #515
• @ShanGor made their first contribution in #516
• @JasonnnW3000 made their first contribution in #533

Full Changelog: v1.0.8...v1.0.9

v1.0.8

What's Changed

• Add LoLLMs Integration to LightRAG by @ParisNeo in #502
• GremlinStorage: support more Gremlin compatible DBs by @alllexx88 in #505
• Added Azure OpenAI api sample with streaming by @congiuluc in #504
• API Installation Options and Documentation Improvements by @ParisNeo in #507
• Fix the issue where the cache is not properly enabled. by @theClassLight in #513

New Contributors

• @congiuluc made their first contribution in #504

Full Changelog: v1.0.7...v1.0.8

v1.0.7

What's Changed

• Add Apache AGE graph storage by @alllexx88 in #465
• refactor(lightrag): Optimize the initialization logic of by @theClassLight in #477
• fix(llm): Fix the initialization issue of by @theClassLight in #479
• support TiDBGraphStorage by @Weaxs in #483
• Added ollama and openai Fastapi api services by @ParisNeo in #482
• Add Gremlin graph storage by @alllexx88 in #494

New Contributors

• @alllexx88 made their first contribution in #465
• @theClassLight made their first contribution in #477
• @ParisNeo made their first contribution in #482

Full Changelog: v1.0.6...v1.0.7

v1.0.6

What's Changed

• chore: update llm.py by @eltociear in #436
• fix(lightrag): Fix the logic for handling chunks with entities but no relationships by @magicyuan876 in #443
• Fix/lazy import by @davidleon in #444
• fix: rare embedding issue. by @davidleon in #440
• Feature/add concurrent embedding limit by @davidleon in #441
• Fix/extra keyword extraction by @davidleon in #442
• feat: Add ChromaDB integration for vector storage by @spo0nman in #447
• support TiDB: add TiDBKVStorage, TiDBVectorDBStorage by @Weaxs in #452
• fix: fix variable name(entitiy->entity) by @ChenZiHong-Gavin in #458
• fix: update operate.py by @tjyiiuan in #461
• Maybe very important!!! Fix embedding error by @billvsme in #464
• Supporting Zhipu AI API by @JasonGuoo in #462

New Contributors

• @eltociear made their first contribution in #436
• @spo0nman made their first contribution in #447
• @Weaxs made their first contribution in #452
• @tjyiiuan made their first contribution in #461
• @billvsme made their first contribution in #464
• @JasonGuoo made their first contribution in #462

Full Changelog: v1.0.5...v1.0.6

v1.0.5

What's Changed

• Added the ability to use embedding cache during queries by @magicyuan876 in #406
• Fixed a bug where args_hash was not calculated during embedding caching due to only being computed in regular caching scenarios by @magicyuan876 in #408
• Update oracle_impl.py by @zsuroy in #409
• Add support for Ollama streaming output and integrate Open-WebUI as the chat UI demo by @partoneplay in #407
• Refactored caching logic by @magicyuan876 in #412
• Optimized embedding similarity caching mechanism, added LLM similarity check functionality, and improved caching mechanism by @magicyuan876 in #421
• Added Jina embedding support by @davidleon in #423
• Interactive Graph: Mouse hover on nodes and edges displays description in a pop-up window by @kaushikacharya in #424
• Fixed a bug #306 by @magicyuan876 in #428
• Fix: Ensure entity_or_relation_name is a string in _handle_entity_relation_summary by @SaujanyaV in #415
• Add an Ollama API service demo by @zhenya-zhu in #430
• Add support for OpenAI-compatible streaming output and delete unreachable code by @partoneplay in #417
• Fix: SyntaxError by @guyuecode in #425
• Fix extra kwargs error: keyword_extraction by @davidleon in #429
• Fix (LightRAG): Use is_closed() instead of _closed by @ChenZiHong-Gavin in #432
• Fix Unicode escape for cases like "/utils" in the response by @davidleon in #435
• Optimized keyword extraction prompt by @magicyuan876 in #434

New Contributors

• @zsuroy made their first contribution in #409
• @kaushikacharya made their first contribution in #424
• @SaujanyaV made their first contribution in #415
• @zhenya-zhu made their first contribution in #430
• @guyuecode made their first contribution in #425
• @ChenZiHong-Gavin made their first contribution in #432

Full Changelog: v1.0.4...v1.0.5