A demo to show how MS-GraphRAG can be used to enable agents access to large corpus of knowledge stored in knowledge graphs.

This project is part of the 2025 LLM hackathon for materials and chemistry! (Team GoldKnowledge Retrievers)

This demo uses the MOF-ChemUnity knowledge graph. It contains information about metal-organic frameworks from different sources.

First install the dependencies from the requirements.txt file (it is highly encouraged to use a separate virtual enviroment):

pip install -r requirements.txt

All you need is to add your OpenAI API key to the Agent.ipynb notebook and run all cells.