HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Constructs a dual-level retrieval system combining vector similarity search with knowledge graph extraction to handle both entity-centric and content-based queries. Supports multiple storage backends including Neo4j, MongoDB, and PostgreSQL, with integrated reranking, citation tracking, and multimodal document processing via RAG-Anything. Designed for Python 3.10+ with built-in evaluation (RAGAS) and tracing (Langfuse) capabilities.
29,302 stars. Actively maintained with 494 commits in the last 30 days.
Stars
29,302
Forks
4,198
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
494
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/HKUDS/LightRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
DataScienceUIBK/Rankify
🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented...