GraphAcademy
Course

Neo4j and Generative AI Workshop

Learn how to build GraphRAG workflows with Neo4j, Python, and LLM-powered retrieval techniques.

2 hours17 lessons across 4 modules
About this workshop

In this 2-hour workshop, you will learn

Welcome to GraphAcademy and the Neo4j and Generative AI workshop.

In this workshop you will:

  • Learn about Generative AI, RAG, and GraphRAG.
  • Build a knowledge graph from unstructured and structured data.
  • Use Vector indexes and embeddings in Neo4j to perform similarity search.
  • Create vector, vector + cypher, and text to Cypher retrievers.
  • Build a conversational agent using Neo4j, Python, and LangChain

Prerequisites

Before taking this workshop, you should have:

  • A basic understanding of Graph Databases and Neo4j
  • Able to read and understand basic Cypher queries
  • Knowledge of Python and capable of reading and executing simple programs

To take this course we recommend that you have taken these beginner courses in GraphAcademy:

  • The fundamentals of Generative AI and Large Language Models (LLMs)

  • What Retrieval-Augmented Generation (RAG) is and why it is important

  • How GraphRAG can improve the quality of LLM-generated content

  • How to build knowledge graphs from unstructured PDF documents using entity extraction and relationship mapping

  • How to enrich knowledge graphs with structured data

  • How to use Vectors in Neo4j for similarity search

  • To build different types of retrievers using the neo4j-graphrag for Python package.

  • To build a conversational agent using Neo4j, Python, and LangChain.

Before you start

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.

    Sign in or create an account

  • A GitHub account, or Git on your own machine

    You write code against the workshop-genai 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.

Course content

4 modules, 2 hours.

  1. 4 lessons
    1. What is Generative AI5 min
    2. GraphRAG?5 min
    3. What is a Knowledge Graph5 min
    4. GraphRAG for Python5 min
  2. 7 lessons
    1. Constructing knowledge graphs5 min
    2. Extracting a schema from text5 min
    3. Create a graph5 min
    4. Chunk size5 min
    5. Define a schema5 min
    6. Add structured data to the knowledge graph5 min
    7. Create your own knowledge graphOptional5 min
  3. 3 lessons
    1. Vector RAG5 min
    2. Vector + Cypher retriever5 min
    3. Text to Cypher retriever5 min
  4. 5 lessons
    1. What is an Agent?5 min
    2. LangChain Agent5 min
    3. Search lesson content5 min
    4. Query database5 min
    5. Create an agentOptional5 min