Graph Database - Amsterdam

This session is designed to show you the basics of Neo4j by explaining the core concepts of graph databases, such as nodes, relationships, properties, and labels. You will learn how graph databases offer a more intuitive and flexible approach to data than traditional relational databases.

The workshop will include hands-on exercises to introduce you to Cypher, Neo4j’s query language. You will create Cypher queries to read and write data in a Neo4j database. This will get you started to explore the possibilities of graph databases further and apply your new knowledge to real-world scenarios, making it an ideal starting point for developers, data scientists, and technology enthusiasts interested in deploying the capabilities of Neo4j.

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.