Find tools › Open-source projects › Chat with your files

LightRAG

Open-source project · by HKUDS

A code toolkit that lets AI answer questions about your documents by mapping how their ideas connect.

For developersPopular154,433 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Ask questions across a big pile of reports
  • Build a Q&A assistant for company manuals
  • See how people, places, and topics in documents connect

How to start

  1. Have Python installed and an AI provider key ready.

  2. In a terminal, run pip install lightrag-hku.

  3. Follow the README examples to load documents and ask questions.

Good to know. The project integrates many external services like MinerU, Docling, and various vector and graph databases, which can add complexity to your setup.

Before you install

  • Checked by a personWe read what it does before listing it.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

LightRAG is a simple and fast retrieval-augmented generation framework that uses dual-level retrieval and knowledge graphs to answer questions from your documents.

Traditional RAG struggles with complex queries that require connecting multiple pieces of information across large text corpora. Reach for LightRAG when you need an efficient, graph-based RAG system that supports multimodal data parsing, multiple storage backends, and role-specific LLM configurations.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map