agentskillexchange LightRAG Graph-Based Retrieval-Augmented Generation Framework
LightRAG is a Python-based retrieval-augmented generation framework that builds knowledge graphs from documents for more connected, contextual retrieval. Published at EMNLP 2025, it enables graph-powered RAG with support for multiple storage backends and LLM providers.
Installation
Use the upstream install or setup path that matches your environment:
- Note: You can also use pip if you prefer, but uv is recommended for better performance and more reliable dependency management.
- uv tool install "lightrag-hku[api]"
- git clone https://github.com/HKUDS/LightRAG.git
- make dev
Requirements and caveats from upstream:
- [2026.03]🎯[New Feature]: Introduced a setup wizard. Support for local deployment of embedding, reranking, and storage backends via Docker.
python -m venv .venv
Basic usage or getting-started notes:
📦 Offline Deployment: For offline or air-gapped environments, see the Offline Deployment Guide for instructions on pre-installing all dependencies and cache files.
The LightRAG Server is designed to provide Web UI and API support. The Web UI facilitates document indexing, knowledge graph exploration, and a simple RAG query interface. LightRAG Server also provide an Ollama compat...
Install from PyPI
Extracted from upstream docs: https://raw.githubusercontent.com/HKUDS/LightRAG/HEAD/README.md