https://github.com/awslabs/graphrag-toolkit

Python toolkit for building graph-enhanced GenAI applications
https://github.com/awslabs/graphrag-toolkit

amazon-neptune amazon-opensearch-serverless graph-database graphrag llama-index mcp postgresql

Last synced: 16 days ago
JSON representation

Python toolkit for building graph-enhanced GenAI applications

• Host: GitHub
• URL: https://github.com/awslabs/graphrag-toolkit
• Owner: awslabs
• License: apache-2.0
• Created: 2024-11-15T10:05:01.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2026-02-03T16:56:03.000Z (29 days ago)
• Last Synced: 2026-02-04T06:28:19.841Z (29 days ago)
• Topics: amazon-neptune, amazon-opensearch-serverless, graph-database, graphrag, llama-index, mcp, postgresql
• Language: Python
• Homepage:
• Size: 74.6 MB
• Stars: 358
• Watchers: 20
• Forks: 68
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Security: security.md
  • Notice: NOTICE

Awesome Lists containing this project

• awesome-mcp - awslabs/graphrag-toolkit - The graphrag-toolkit is a Python toolkit for building graph-enhanced Generative AI applications, featuring BYOKG-RAG for knowledge graph question answering and an MCP server for dynamic tool generation in multi-tenant environments. (MCP Frameworks and libraries / Python)
• awesome-github-repos - awslabs/graphrag-toolkit - Python toolkit for building graph-enhanced GenAI applications (Python)

README

          
## GraphRAG Toolkit

The graphrag-toolkit is a collection of Python tools for building graph-enhanced Generative AI applications.

Installation instructions and requirements are detailed separately with each tool.

### Lexical Graph

The [lexical-graph](./lexical-graph/) provides a framework for automating the construction of a [hierarchical lexical graph](./docs/lexical-graph/graph-model.md) from unstructured data, and composing question-answering strategies that query this graph when answering user questions.

![Lexical graph](./images/visualisation.png)

### BYOKG-RAG

[BYOKG-RAG](./byokg-rag/) is a novel approach to Knowledge Graph Question Answering (KGQA) that combines the power of Large Language Models (LLMs) with structured knowledge graphs. The system allows users to bring their own knowledge graph and perform complex question answering over it.

## Security

See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.

## License

This project is licensed under the Apache-2.0 License.