Retrieval Augmented Generation (RAG)

Module Overview

In this module, you will learn:

  • What Retrieval Augmented Generation (RAG) is and how it combines understanding user queries, retrieving relevant information, and generating responses using that information.

  • How vectors and embeddings work, and how they can be used in RAG to find relevant information.

  • How to use a vector index in Neo4j and when vector indexes are useful for finding context for Generative AI applications.

  • What GraphRAG techniques are, and how they can be used to enhance information retrieval by combining vector search with graph traversal and relationships.

If you are ready, let’s get going!

Ready? Let’s go →