STAGS

LightRAG

80 versions indexed · latest v1.5.8rc1 on Nov 15, 2026

HKUDS/LightRAG ↗

202619

v1.5.8rc1 patch ZH

1. Configuration storage: LightRAG now remembers which embedding model built your vectors

v1.5.7 patch ZH

New Feature: Add end-user-facing entry point to WebUI

v1.5.7rc2 patch ZH

Add an offline tool to migrate a graph from Apache AGE to PostgreSQL tables · feat: support graph-first ingestion with deferred vector indexing · feat: add explicit custom chunking selector

v1.5.6 patch ZH

Introducing PGTableGraphStorage, a new graph storage backend built on native PostgreSQL tables. By eliminating the dependency on Apache AGE, it not only simplifies deployment but also delivers significantly higher graph…

v1.5.5 patch ZH

Starting from v1.5.5, LightRAG's built-in DOCX parser introduces the Smart Heading feature -- enabling better section-based chunking even for poorly formatted DOCX documents.

v1.5.4 patch ZH

feat(parser): native engine support for Markdown parsing, including embedded base64 images and .textpack bundle image integration · feat(parser): per-file engine parameters via hint/rule (Phase 2 — MinerU + Docling)

v1.5.3 patch ZH

Due to PR #3228, upgrading an existing Milvus deployment triggers a one-time automatic migration on the next initialize_storages(): the legacy collection is copied into the new model-suffixed collection (schema-upgraded…

v1.5.2 patch ZH

feat(parser): standardize the parser engine interface through a registration mechanism with support for third-party parsers

v1.5.1 patch ZH

To prevent weaker LLMs from inadvertently incorporating few-shot examples from the prompt into the extraction results, the official entity-relation extraction prompt has been updated in the current version by removing…

v1.5.0 minor ZH

🎉✨Feacture: LightRAG now supports multimodal document processing and can fully leverage images, tables, and formulas within documents to answer queries.

v1.4.16 patch ZH

It's a breaking change for existing deployments on OpenSearch < 3.3.0. OpenSearch: Use version-aware sort tiebreaker for PIT search

v1.4.15 patch ZH

ci: sign GHCR docker images with cosign · feat(embeddings): added embedding support for providers that don't support base64 encoding (e.g. Yandex Cloud)

v1.4.14 patch ZH

feat(setup): support Atlas Local Docker for Mongo vector storage · perf: batch graph operations in ainsert_custom_kg for large-scale imports · examples: add AG2 multi-agent demo with LightRAG retrieval

v1.4.13 patch ZH

Feat: add make dev bootstrap target · Feat: Add PostgreSQL performance timing instrumentation

v1.4.12 patch ZH

Optimize Postgres Vector DB upsert performance by increasing the batch size to 200 records per operation. · Resolved issue with opening PDF files protected by permission-only restrictions

v1.4.11 patch ZH

Integrated OpenSearch as a unified storage backend, providing comprehensive support for all four LightRAG storage types: KV, Vector, Graph, and DocStatus.

v1.4.11rc2 patch ZH

Add Makefile for quick deployment · Refactor(Makefile): split monolithic wizard into modular env-base/storage/server targets

v1.4.10 patch ZH

feat: Add POSTGRES_ENABLE_VECTOR option to conditionally disable pgvector extension · Add i18n support for Vietnamese

v1.4.9.11 patch ZH

Fix OpenAI LLM binding options not loaded from environment variables

202556

v1.4.9.10 patch ZH

Hot Fix AttributeError in Neo4JStorage and MemgraphStorage when using storage specified workspace env var

v1.4.9.9 patch ZH

Add Workspace Isolation for Pipeline Status and In-memory Storage: Multiple LightRAG instances with distinct workspaces can be created simultaneously, marking a significant advancement toward seamless workspace…

v1.4.9.8 patch ZH

Feat: Add PDF Decryption Support for Password-Protected Files · Feat: Add optional Langfuse observability integration · Feat: Add RAGAS evaluation framework for RAG quality assessment

v1.4.9.7 patch ZH

This update requires qdrant-client version 1.11.0 or later (due to the use of tenant indexing) when using Qdrant. Data migration may take a significant amount of time for large datasets.

v1.4.9.6 patch ZH

Restore query generation example and fix README path reference · Refact: Graceful shutdown and signal handling in Gunicorn Mode · HotFix: Include swagger-docs static files in package distribution

v1.4.9.5 patch ZH

🚀 PostgreSQL migration performance problem for large dataset in v1.4.9.4 · 🛑 Introduces a graceful pipeline cancellation mechanism for document processing operations

v1.4.9.4 patch ZH

In production deployments, entity and relation metadata can grow unbounded as documents are continuously ingested. The source_id (chunk IDs) and file_path fields in entities and relations can accumulate thousands of…

v1.4.9.3 patch ZH

Add temporary solution implemented to ensure compatibility with the newly introduced document status in Rayanything.

v1.4.9.2 patch ZH

feat: Add endpoint and UI to retry failed documents · Refactor(webui): Improve document tooltip display with track ID and better formatting · feat: add options for Postgres connection

v1.4.9.1 patch ZH

Feature(webui): Add KaTeX chemical formula rendering by supporting mhchem extension · Feat(webui): Prevent LaTeX Parsing Errors Show-up During Streaming · Fix dark mode graph labels for system theme and improve colors

v1.4.9 patch ZH

v1.4.9 introduces key enhancements focused on refining the reference output format and incorporating structured references into query results.

v1.4.8.2 patch ZH

Refactor: Add error handling with chunk ID prefixing in entity extraction · fix: resolve dark mode text visibility issue in knowledge graph view · Fix: Resolve DocumentManager UI freezing and enhance error handling

v1.4.8 patch ZH

Introduced a raw data query API /query/data, enabling developers to retrieve complete raw data recalled by LightRAG for fine-grained processing.

v1.4.8rc9 patch ZH

Prompt Optimization: remove angle brackets from entity and relationship output formats · Refactor PostgreSQL Graph Query by Native SQL and Standardized Parameter Passing

v1.4.8rc8 patch ZH

Optimize Entity Extraction for Small Parameter LLMs with Enhanced Prompt Caching · Add LLM COT Rendering support for WebUI · Enhance document status display with metadata tooltips

v1.4.8rc4 patch ZH

Refactoring Prompt Template and enhancing robust mal-format handling for Knowledge Graph (KG) extraction using Small Parameter Language Models (LLMs). This will invalidate all cached LLM outputs.

v1.4.7 patch ZH

Doc-id based chunk filtering feature is remove from PostgreSQL vector storage. · Prompt template has been updated, invalidating all LLM caches

v1.4.6 patch ZH

feat(performance): Optimize Document Deletion Performance with Entity/Relation Indexing · refactor: improve JSON parsing reliability with json-repair library

v1.4.5 patch ZH

Feat(webui): add document list pagination for webui · Feat: add Document Processing Track ID Support for Frontend · Better prompt for entity description extraction to avoid hallucinations

v1.4.4 patch ZH

Refac: optimizing context builder to improve query performance · Improve query for find_text_unit · feat: Integrate Jina embeddings API support · feat: Add SSL support for PostgreSQL database connections

v1.4.3 patch ZH

Feat: change default query mode from hybrid to mix · Add Azure deployment · Remove separate requirements.txt and update Dockerfile to use pip install

v1.4.2 patch ZH

Fix Milvus DataNotMatchException · fix: change default edge weight from 0.0 to 1.0 in entity extraction and graph storage

v1.4.1 patch ZH

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

v1.4.0 minor ZH

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.

v1.3.9 patch ZH

docs: Add clear initialization requirements and troubleshooting section · Add doc for explaining LightRAG's multi-document concurrent processing mechanism

v1.3.8 patch ZH

Fix: Correct GraphML to JSON mapping in xml_to_json function · Fix js files MIME type error for Windows environment · Reflect core library parameter update in API server

v1.3.7 patch ZH

Feat: Add user prompt to QueryParam · Deduplicate merged relation keywords · Allow max_connections to be configured in postgres · Persistent LLM cache on error

v1.3.6 patch ZH

Hotfix: Resolve send button not working for some old version browser for crypto.randomUUID · Improve parallel processing logic for document extraction and merging

v1.3.5 patch ZH

Resolved missing dependency issues during PyPI package installation via pip

v1.3.4 patch ZH

Feat: Add Markdown & Mermaid support for WebUI · Feat: add custom tokenizer · Feat: Add query mode prefix support in retrieval test of WebUI · Improve PostgreSQL AGE query speed by write a customized BFS implementation

v1.3.3 patch ZH

Resolved special character handling issue in PostgreSQL graph storage · Properly handling of backslashes and quotation marks in entity and relation names

v1.3.2 patch ZH

Key improvements: Enhanced document indexing speed. Significantly improved the query performance of Neo4j and PostgreSQL AGE graph storage.

v1.3.1 patch ZH

Refactoring PostgreSQL AGE graph storage implementation, which introducing breaking changes that are incompatible with existing graph data

v1.3.0 minor ZH

refactor(SiteHeader): Hide logout button in guest mode · Refactor auth and version checks for improved reliability · Refactor LightRAG Server documentation for clarity and structure. · Fix mongo doc status

v1.2.8 patch ZH

Optimize parallel file processing in folder scan · Fix dead lock problem in Gunicorn multi workers mode · Fix empty graph not display correctly after database dropped

v1.2.7 patch ZH

Added camera rotation to graph panel and merge login feature · Added loginPage · Fixed get_by_id type error in PSQL impl · Hot fix: Server can not startup with legacy data (json_doc_status_impl.py)

v1.2.6 patch ZH

Resolve the issue with making API calls to Azure OpenAI service · force keywords_extraction output as JSON · Improve Entity Extraction Robustness for Truncated LLM Responses · Filter by ID during Query for Postgres VDB

v1.2.5 patch ZH

Add summary language setting by env · Completed the missing methods in various databases to support modifications for the Graph. · Made .env file loaded from the current folder instead of the script folder

v1.2.4 patch ZH

Add multi workers support for API Server · adding full_doc_id to insert · Improved caching check · Add max nodes limit for graph retrieval

v1.2.3 patch ZH

Use consistent format as in examples · feat: fix delete by document id

v1.2.2 patch ZH

fix AttributeError: 'NoneType' object has no attribute 'dim' · Add retrieval message code highlighting and copy button · Enhance Graph Visualization with Configurable Depth and Layout Iterations

v1.2.1 patch ZH

Added more file types support to the webui · Simplify dockerfile and docker-compose files · add support of providing ids for documents insert · fix insert_custom_chunks skipping every new doc

v1.1.12 patch ZH
v1.1.11 patch ZH

Revert 'removed get_knowledge_graph' · Updated version to 1.1.11

v1.1.10 patch ZH

Template github · updated template · Updated templates · Removed all useless try except around imports as pipmaster already handles that

v1.1.9 patch ZH

Fix ImportError by Removing Redundant Try-Except Block

v1.1.8 patch ZH

Cleaned typing · Lightrag Server Launch fix. · fixed missing install · Refactor Database Connection Management and Improve Storage Lifecycle Handling

v1.1.7 patch ZH

chroma_impl supports local persistent client: PersistentClient · Add MongoDB VectorDB Support and Optimize Existing MongoDB Implementations · Enhance Neo4j graph storage with error handling and label validation

v1.1.6 patch ZH

Improve LLM Error Handling for API Server · Split ollama api to separated file · fix graph viewer crash on macos when show file dialog · Fixing .env file loading problem for Ollama API module

v1.1.5 patch ZH

Fix broken main · feat: Added webui management, including file upload, text upload, Q&… · Add history support for ollama api · fix README

v1.1.4 patch ZH

Fixed API docs link in Readme.md · Addind a simple tool to view the lightrag database in 3d · Replacing ParisNeo with this repo owner, HKUDS

v1.1.3 patch ZH

Major Updates: Docker Support, Enhanced Configuration, and Documentation Restructuring #554 · add readme_zh · Add Ollama compatible API server · Fixes #596 - Hardcoded model deployment name in azure_openai_complete

v1.1.2 patch ZH

Fix for mongoDB document 16MB limit and add os env NEO4J_MAX_CONNECTION_POOL_SIZE for neo4j · Enhancement: Multi-format document support and dynamic dependency management #565

v1.1.1 patch ZH

Add character segmentation functionality for chunks · Fix:Optimized logic for automatic switching modes when keywords do not exist · Implement custom chunking feature

v1.1.0 minor ZH

Add Optional API Key Authentication to FastAPI Services · Added PostgreSQL implementation · Add support for selecting a specific database in Neo4j

v1.0.9 patch ZH

Streamlined API Installation and Documentation Enhancement · Fixed keywords_extraction_examples format error · Fixed the async issue while running on Windows

20245

v1.0.8 patch ZH

Add LoLLMs Integration to LightRAG · GremlinStorage: support more Gremlin compatible DBs · Added Azure OpenAI api sample with streaming · API Installation Options and Documentation Improvements

v1.0.7 patch ZH

Add Apache AGE graph storage · refactor(lightrag): Optimize the initialization logic of · fix(llm): Fix the initialization issue of · support TiDBGraphStorage

v1.0.6 patch ZH

chore: update llm.py · fix(lightrag): Fix the logic for handling chunks with entities but no relationships · Fix/lazy import · fix: rare embedding issue.

v1.0.5 patch ZH

Added the ability to use embedding cache during queries · Fixed a bug where args_hash was not calculated during embedding caching due to only being computed in regular caching scenarios · Update oracle_impl.py

v1.0.4 patch ZH

Add MongoDB as KV storage · Fix JSON parsing error