Skills
.Work. You
Rest

lightrag

Official

Turn documents into graph-aware Q&A

Data & Analytics#knowledge graph#semantic search#rag#vector embeddings#document q&a#entity extraction#graphrag
AuthorRoentek
Version1.0.0
Installs0

System Documentation

What problem does it solve?

LightRAG helps you extract relationships and structured knowledge from documents so your Q&A can answer with graph-aware context instead of relying only on naive text similarity.

Core Features & Use Cases

  • Graph-based RAG: builds an entity/relationship knowledge graph from your source documents and uses it for entity-aware retrieval and Q&A.
  • Multiple query modes: supports naive, local, global, hybrid, and mix workflows to balance speed and answer quality.
  • Pluggable backends: persists the graph in storage backends like nano-vectordb (default), Neo4J, MongoDB, or PostgreSQL for different production needs.

Quick Start

Start by installing dependencies with uv in tools/lightrag, then configure one LLM provider API key in .env and use the provided LightRAG code (or start the server) to insert documents and query them with hybrid retrieval.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: lightrag
Download link: https://github.com/Roentek/Claude_Code_Boilerplate_Framework/archive/main.zip#lightrag

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.