Graph Database - San Francisco

Take your AI applications to the next level by mastering GraphRAG in this exclusive Neo4j virtual workshop. Discover how to use the neo4j-graphrag open-source python package to build and optimize Retrieval-Augmented Generation (RAG) systems seamlessly integrated with generative AI models.

This workshop introduces you to GraphRAG and you will learn how to convert unstructured documents into structured graphs using the Neo4j Labs LLM Graph Builder.
Through hands-on exercises, you'll build your own knowledge graph from text, visualize the structure, and interact with it using Python. This session is ideal for anyone looking to understand their documents beyond simple keyword search, using graph techniques to uncover relationships and surface insights.

This workshop takes you from theory to practice with a fully operational hybrid Retrieval-Augmented Generation (RAG) pipeline - built live in Neo4j. You'll learn how to combine traditional BM25 search with dense vector similarity and graph-native expansion to power more accurate and explainable results.
Over the course of two hours, you’ll create a knowledge graph, run hybrid retrieval directly in the database, and integrate your results into a LangChain-powered RAG application. You’ll leave with a working system you can run on your own machine, complete with a GitHub repo ready for production use.

This hands-on workshop shows you how to build smarter AI agents: ones that don’t lose context. You’ll use Neo4j’s Model Context Protocol (MCP) to give your agents persistent, graph-based memory, allowing for richer, multi-turn interactions and intelligent behavior grounded in your data.

You’ll walk through the full agent-building process: from setting up a knowledge graph, to integrating GraphRAG for multi-hop reasoning, and deploying an agent with contextual memory that evolves over time. By the end of the session, you’ll have a working, production-ready AI agent you can extend for your own use cases.