HKUDS/LightRAG

Health v2 · maintenance only

Adoption not part of the score

40153 stars · 5702 forks observed · 2026-10-16

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.97

LightRAG is a Python library that implements a simple and fast Retrieval-Augmented Generation framework using graph structures and vector embeddings. It enables LLMs to retrieve and reason over external knowledge with high efficiency.

Use cases

• Enhance a large language model with up‑to‑date knowledge from a document corpus
• Build a chatbot that can answer questions using a knowledge graph
• Create a search system that returns both relevant passages and their relationships
• Implement incremental updates to a retrieval index without full re‑indexing
• Develop a RAG pipeline for enterprise document assistants

When to choose

• You need a lightweight RAG solution that combines graph‑based retrieval with vector similarity
• Your project is Python‑centric and you want easy integration with existing LLM APIs
• Fast response times are critical and you want incremental index updates
• You want to leverage entity relationships in the retrieval process

When to avoid

• You require a fully managed cloud RAG service with built‑in scaling
• Your stack is not Python and you cannot use the library directly
• You need deep customisation of the underlying retrieval engine beyond what LightRAG exposes

Facets

library · maturity active

rag vector-database search-engine llm-inference api-framework large-language-models artificial-intelligence data-science python windows knowledge-graph graph-rag incremental-update fast-retrieval open-source graph retrieval-augmented-generation linux macos docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="HKUDS/LightRAG")