graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
What is graphrag?
A modular graph-based Retrieval-Augmented Generation (RAG) system
Overview of graphrag
What it is
GraphRAG is a modular graph-based Retrieval-Augmented Generation (RAG) system developed by Microsoft Research. It is a data pipeline and transformation suite designed to extract meaningful, structured data from unstructured text using the power of large language models (LLMs). The project is currently in maintenance mode, meaning it will not accept new pull requests or implement new features, but will continue to receive bug fixes and dependency updates.
Key features
- Extracts structured data from unstructured text using LLMs - Uses knowledge graph memory structures to enhance LLM outputs - Provides a data pipeline and transformation suite for processing text - Designed to form targeted context for question answering - Includes prompt tuning guidance for better results with custom data - Offers a command-line interface for quickstart and configuration - Supports versioning with migration notebooks for major version bumps
Use cases
GraphRAG is intended to enhance an LLM's ability to reason about private or domain-specific data by building a knowledge graph from unstructured text. It can be used for question answering over large document collections, research analysis, and any scenario where structured context from unstructured sources is needed.
Getting started
To get started with GraphRAG, see the command line quickstart in the repository README. No specific installation or quick-start commands are provided in the README.
License and pricing
GraphRAG is licensed under the MIT License and is open source. No pricing information is provided.
Based on the project's public README and repository metadata.