A modular graph-based Retrieval-Augmented Generation (RAG) system
Go to file
2024-07-01 16:28:32 -06:00
.github Fix publishing (#315) 2024-07-01 16:28:32 -06:00
.semversioner Release v0.1.0 (#313) 2024-07-01 15:54:44 -06:00
.vscode Initial Release 2024-07-01 15:25:30 -06:00
docsite Initial Release 2024-07-01 15:25:30 -06:00
examples Initial Release 2024-07-01 15:25:30 -06:00
examples_notebooks Initial Release 2024-07-01 15:25:30 -06:00
graphrag Initial Release 2024-07-01 15:25:30 -06:00
scripts Initial Release 2024-07-01 15:25:30 -06:00
tests Initial Release 2024-07-01 15:25:30 -06:00
.gitignore Initial Release 2024-07-01 15:25:30 -06:00
.vsts-ci.yml Initial Release 2024-07-01 15:25:30 -06:00
CODE_OF_CONDUCT.md Initial Release 2024-07-01 15:25:30 -06:00
CODEOWNERS Initial Release 2024-07-01 15:25:30 -06:00
CONTRIBUTING.md Initial Release 2024-07-01 15:25:30 -06:00
cspell.config.yaml Initial Release 2024-07-01 15:25:30 -06:00
DEVELOPING.md Initial Release 2024-07-01 15:25:30 -06:00
dictionary.txt Initial Release 2024-07-01 15:25:30 -06:00
LICENSE Initial Release 2024-07-01 15:25:30 -06:00
poetry.lock Initial Release 2024-07-01 15:25:30 -06:00
pyproject.toml Release v0.1.0 (#313) 2024-07-01 15:54:44 -06:00
RAI_TRANSPARENCY.md Initial Release 2024-07-01 15:25:30 -06:00
README.md Initial Release 2024-07-01 15:25:30 -06:00
SECURITY.md Initial Release 2024-07-01 15:25:30 -06:00
SUPPORT.md Initial Release 2024-07-01 15:25:30 -06:00

GraphRAG

👉 Use the GraphRAG Accelerator solution 👉 Microsoft Research Blog Post 👉 Read the docs

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 LLMs ability to reason about your private data, please visit the Microsoft Research Blog Post.

Quickstart

To get started with the GraphRAG system we recommend trying the Solution Accelerator package. This provides a user-friendly end-to-end experience with Azure resources.

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.

Diving Deeper

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.

Responsible AI FAQ

See RAI_TRANSPARENCY.md

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