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

graphrag

Open-source project · by microsoft

Microsoft's tool that turns piles of text into a map of connected facts AI can answer questions from.

Some setupPopular48,552 installs a month

What it costs

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

Use it to

  • Answer big-picture questions across hundreds of documents
  • Pull out people, companies, and links from reports
  • Summarize themes across a large text collection

How to start

  1. Prefer an alternative: LightRAG, since GraphRAG is largely in maintenance mode.

  2. Read the cost docs first; indexing can use a lot of paid AI tokens.

  3. In a terminal, set up a project with graphrag init --root [path] --force.

  4. Start with a small set of documents, then follow the docs to index and ask questions.

Good to know. The project is largely in maintenance mode. Indexing can be an expensive operation with high LLM token costs, so start small and read the cost documentation carefully.

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 2026-11-16

More detail

A data pipeline and transformation suite designed to extract structured data from unstructured text using LLMs to build knowledge graphs for question answering.

It improves LLM reasoning over private datasets by organizing text into structured knowledge graphs. Reach for it when standard vector search RAG struggles to connect disparate facts across large corpora.

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