GraphRAG

What's Changed

• feat: native CosmosTableProvider with namespace partitioning by @disamhembere in https://github.com/microsoft/graphrag/pull/2354
• Update litellm dependency. by @dworthen in https://github.com/microsoft/graphrag/pull/2365
• Release v3.1.0 by @dworthen in https://github.com/microsoft/graphrag/pull/2366
• Update getting started docs. by @dworthen in https://github.com/microsoft/graphrag/pull/2367
• Fix logging bug. by @dworthen in https://github.com/microsoft/graphrag/pull/2429
• Loosen service_tier type to str | None to allow for more flexibility … by @dworthen in https://github.com/microsoft/graphrag/pull/2430
• Fix .strip call by @dworthen in https://github.com/microsoft/graphrag/pull/2431
• Dep sweep by @dworthen in https://github.com/microsoft/graphrag/pull/2441
• Missing return type hints on generator functions in query/llm/text_utils.py by @gaudyb in https://github.com/microsoft/graphrag/pull/2443
• Issue 2265: Column length mismatch by @gaudyb in https://github.com/microsoft/graphrag/pull/2442
• Fix cannot release un-acquired lock in Blob logger by @gaudyb in https://github.com/microsoft/graphrag/pull/2457
• Sync docs for schema and metadata fields by @natoverse in https://github.com/microsoft/graphrag/pull/2435
• Fix JSONL loader handling of blank/invalid lines by @natoverse in https://github.com/microsoft/graphrag/pull/2434
• Release v3.1.1 by @gaudyb in https://github.com/microsoft/graphrag/pull/2458

New Contributors

• @disamhembere made their first contribution in https://github.com/microsoft/graphrag/pull/2354

Full Changelog: https://github.com/microsoft/graphrag/compare/3.0.9...v3.1.1

GraphRAG

👉 Microsoft Research Blog Post<br/>

👉 Read the docs<br/>

👉 GraphRAG Arxiv

<div align="left">

<a href="https://pypi.org/project/graphrag/">

<img alt="PyPI - Version" src="https://img.shields.io/pypi/v/graphrag">

</a>

<a href="https://pypi.org/project/graphrag/">

<img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/graphrag">

</a>

<a href="https://github.com/microsoft/graphrag/issues">

<img alt="GitHub Issues" src="https://img.shields.io/github/issues/microsoft/graphrag">

</a>

<a href="https://github.com/microsoft/graphrag/discussions">

<img alt="GitHub Discussions" src="https://img.shields.io/github/discussions/microsoft/graphrag">

</a>

</div>

Overview

The GraphRAG project is a data pipeline and transformation suite that is designed to extract meaningful, structured data from unstructured text using the power of LLMs.

To learn more about GraphRAG and how it can be used to enhance your LLM's ability to reason about your private data, please visit the <a href="https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/" target="_blank">Microsoft Research Blog Post.</a>

Quickstart

To get started with the GraphRAG system we recommend trying the command line quickstart.

Repository Guidance

This repository presents a methodology for using knowledge graph memory structures to enhance LLM outputs. Please note that the provided code serves as a demonstration and is not an officially supported Microsoft offering.

⚠️ Warning: GraphRAG indexing can be an expensive operation, please read all of the documentation to understand the process and costs involved, and start small.

Diving Deeper

• To learn about our contribution guidelines, see CONTRIBUTING.md
• To start developing _GraphRAG_, see DEVELOPING.md
• Join the conversation and provide feedback in the GitHub Discussions tab!

Prompt Tuning

Using _GraphRAG_ with your data out of the box may not yield the best possible results.

We strongly recommend to fine-tune your prompts following the Prompt Tuning Guide in our documentation.

Versioning

Please see the breaking changes document for notes on our approach to versioning the project.

Always run graphrag init --root [path] --force between minor version bumps to ensure you have the latest config format. Run the provided migration notebook between major version bumps if you want to avoid re-indexing prior datasets. Note that this will overwrite your configuration and prompts, so backup if necessary.

Responsible AI FAQ

See RAI_TRANSPARENCY.md

• What is GraphRAG?
• What can GraphRAG do?
• What are GraphRAG’s intended use(s)?
• How was GraphRAG evaluated? What metrics are used to measure performance?
• What are the limitations of GraphRAG? How can users minimize the impact of GraphRAG’s limitations when using the system?
• What operational factors and settings allow for effective and responsible use of GraphRAG?

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft

trademarks or logos is subject to and must follow

Microsoft's Trademark & Brand Guidelines.

Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.

Any use of third-party trademarks or logos are subject to those third-party's policies.

Privacy

Microsoft Privacy Statement