HKUDS/LightRAG

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

73
/ 100
Verified

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.

No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

29,302

Forks

4,198

Language

Python

License

MIT

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.