LightRAG

• Provides Retrieval-Augmented Generation (RAG) capabilities for AI applications.
• Supports document indexing and retrieval from knowledge bases.
• Uses knowledge graph-based retrieval to improve contextual understanding.
• Provides a web-based user interface for document management and RAG queries.
• Provides API support for integrating LightRAG with other applications and services.
• Supports configurable LLM and embedding providers.
• Python-based deployment suitable for self-hosted AI and knowledge management environments.

LightRAG usage:

$ sudo su

$ apt update

$ apt install -y python3 python3-pip python3-venv git build-essential

$ cd /opt

$ git clone https://github.com/HKUDS/LightRAG.git

$ cd LightRAG

$ python3 -m venv .venv

$ source .venv/bin/activate

$ python --version

$ pip --version

$ pip install --upgrade pip

$ pip install "lightrag-hku[api]"

$ Check LightRAG version:

$ pip show lightrag-hku

$ Check installed LightRAG package:

$ python -c "import lightrag; print('LightRAG package: OK')"

$ Prepare configuration:

$ cp env.example .env

$ Edit LLM and embedding configuration:

$ nano .env

$ Start LightRAG Server:

$ lightrag-server

$ Check LightRAG is listening on port 9621:

$ ss -lntp | grep 9621

$ Test LightRAG locally:

$ curl -I http://127.0.0.1:9621

$ Access LightRAG in your browser:

# http://SERVER_IP:9621

Version:

LightRAG version: 1.5.6

Disclaimer:

LightRAG is open-source software distributed under the MIT License. It is not affiliated with, endorsed by, or sponsored by any other company or organization. LightRAG is provided "as is," without any warranty, express or implied. Users utilize this software at their own risk. The developers and contributors are not responsible for any damages, losses, or consequences resulting from the use of the software. Users are encouraged to review and comply with the applicable licensing terms and regulations when deploying and using LightRAG.