GraphRAG Hackathon
Build a GraphRAG application powered by Neo4j and an AI coding agent
In this 43-minute workshop, you will learn
In this hackathon, you will learn the fundamentals of Full definition for GraphRAG (opens in a new tab)Retrieval-augmented generation whose context comes from a knowledge graph, so the model can follow the relationships between facts. and build your own application using your AI coding agent — powered by the GraphAcademy MCP server.
The first 30 minutes cover the essentials: why graphs make Go to glossary for large language model (opens in a new tab)A model trained on text to predict the next token, and so to generate language. smarter, how to model your domain, and how to write Full definition for Cypher (opens in a new tab)Neo4j's implementation of GQL, the ISO standard query language for graph databases. It is declarative: you describe the pattern to find, and the database decides how to find it. queries.
Then it's your turn to build. Your coding agent has access to the GraphAcademy MCP server, which provides everything it needs to help you create a working GraphRAG application.
Prerequisites
This hackathon is designed for developers. You will need:
- A GitHub account (for GitHub Codespaces)
- Basic programming experience in Python or JavaScript/TypeScript
You will create a free Neo4j Go to glossary for Aura (opens in a new tab)Neo4j's fully managed cloud service. account at the start of the session, and the workshop provides temporary access to a hosted language model, so you do not need your own LLM provider API key.
No prior knowledge of Neo4j or graph databases is required.
GraphRAG
Neo4j
Cypher
MCP server
AI agents
What you need to take part.
A GraphAcademy account
The workshop is delivered here on GraphAcademy, so you need to be signed in to work through the lessons and keep your progress. Creating an account is free.
A GitHub account, or Git on your own machine
You write code against the workshop-hackathon repository. The quickest route is a GitHub Codespace, an online editor that clones the code and installs everything for you — that needs a GitHub account.
If you would rather work locally, clone the repository with Git and run it in your own editor instead. No GitHub account is needed for that.
3 modules, 43 minutes.
Workshop AI access
This workshop provides temporary access to a hosted language model. Accept the terms and copy your credentials from within any lesson.
Default model: gpt-4o-mini