Data

Tools

Indexes

Applications

Experiments

Open Source Science

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

Python toolkit for building graph-enhanced GenAI applications

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

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.0%) to scientific vocabulary

Keywords

amazon-neptune amazon-opensearch-serverless graph-database graphrag llama-index mcp postgresql
Last synced: 5 months ago · JSON representation

Repository

Python toolkit for building graph-enhanced GenAI applications

Basic Info
  • Host: GitHub
  • Owner: awslabs
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 46.7 MB
Statistics
  • Stars: 259
  • Watchers: 15
  • Forks: 48
  • Open Issues: 6
  • Releases: 54
Topics
amazon-neptune amazon-opensearch-serverless graph-database graphrag llama-index mcp postgresql
Created over 1 year ago · Last pushed 6 months ago
Metadata Files
Readme Changelog Contributing License Code of conduct Security

README.md

GraphRAG Toolkit

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

1 August 2025 Release 3.11.0 includes a Neo4j graph store for the lexical graph and performance improvements to the traversal-based retriever. FalkorDB support has been moved into a lexical-graph-contrib package.

4 June 2025 Release 3.8.0 includes a separate BYOKG-RAG package, which allows users to bring their own knowledge graph and perform complex question answering over it.

28 May 2025 Release 3.7.0 includes an MCP server that dynamically generates tools and tool descriptions (one per tenant in a multi-tenant graph).

Installation instructions and requirements are detailed separately with each tool.

Lexical Graph

The lexical-graph provides a framework for automating the construction of a hierarchical lexical graph from unstructured data, and composing question-answering strategies that query this graph when answering user questions.

Lexical graph

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 for more information.

License

This project is licensed under the Apache-2.0 License.

Owner

  • Name: Amazon Web Services - Labs
  • Login: awslabs
  • Kind: organization
  • Location: Seattle, WA

AWS Labs

GitHub Events

Total
  • Fork event: 44
  • Create event: 46
  • Issues event: 34
  • Release event: 44
  • Watch event: 210
  • Delete event: 5
  • Member event: 3
  • Issue comment event: 98
  • Push event: 247
  • Public event: 1
  • Pull request review event: 30
  • Pull request review comment event: 34
  • Pull request event: 54
Last Year
  • Fork event: 44
  • Create event: 46
  • Issues event: 34
  • Release event: 44
  • Watch event: 210
  • Delete event: 5
  • Member event: 3
  • Issue comment event: 98
  • Push event: 247
  • Public event: 1
  • Pull request review event: 30
  • Pull request review comment event: 34
  • Pull request event: 54

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 22
  • Total pull requests: 28
  • Average time to close issues: 15 days
  • Average time to close pull requests: 6 days
  • Total issue authors: 21
  • Total pull request authors: 11
  • Average comments per issue: 1.64
  • Average comments per pull request: 0.89
  • Merged pull requests: 12
  • Bot issues: 0
  • Bot pull requests: 3
Past Year
  • Issues: 22
  • Pull requests: 28
  • Average time to close issues: 15 days
  • Average time to close pull requests: 6 days
  • Issue authors: 21
  • Pull request authors: 11
  • Average comments per issue: 1.64
  • Average comments per pull request: 0.89
  • Merged pull requests: 12
  • Bot issues: 0
  • Bot pull requests: 3
View more stats
Top Authors
Issue Authors
  • BoggerByte (2)
  • kmotohas (1)
  • onlinebaba (1)
  • jorisdejonghumainr (1)
  • karthiks3000 (1)
  • madhan-here-now (1)
  • NivAm12 (1)
  • promentol (1)
  • tanya-vedi (1)
  • evanerwee (1)
  • shafkevi (1)
  • andou (1)
  • JayantaDas (1)
  • IzriAsma (1)
  • dipakmeher (1)
Pull Request Authors
  • iansrobinson (6)
  • BoggerByte (5)
  • abdghsl (3)
  • evanerwee (3)
  • dependabot[bot] (3)
  • lwsinclair (2)
  • sojiadeshina (2)
  • aghassel (1)
  • NivAm12 (1)
  • cmavro (1)
  • kingtroga (1)
  • azihsoyn (1)
Top Labels
Issue Labels
Pull Request Labels
dependencies (3) python (2)

Dependencies

pyproject.toml pypi
src/requirements.txt pypi
  • FlagEmbedding ==1.3.2
  • anthropic-bedrock ==0.8.0
  • boto3 ==1.35.24
  • botocore ==1.35.24
  • huggingface-hub ==0.23.5
  • json2xml ==5.0.4
  • llama-index-core ==0.10.53.post1
  • llama-index-embeddings-bedrock ==0.2.1
  • llama-index-llms-bedrock ==0.1.12
  • llama-index-readers-file ==0.1.29
  • llama-index-readers-web ==0.1.22
  • llama-index-vector-stores-opensearch ==0.1.12
  • lru-dict ==1.3.0
  • opensearch-py ==2.7.1
  • pipe ==2.2
  • protobuf ==4.25.3
  • pynvml ==11.5.3
  • pytest ==8.2.2
  • python-dotenv ==1.0.1
  • sentence-transformers ==3.1.1
  • sentencepiece ==0.2.0
  • smart_open ==7.0.4
  • spacy ==3.7.5
  • tfidf_matcher ==0.3.0
  • torch ==2.4.1
  • transformers ==4.44.2
src/setup.py pypi