This talk provides an overview of the current state of Graph RAG (Retrieval-Augmented Generation) and its components. Graph RAG has become an incredible buzz term recently, but at its core, it represents an extension to RAG by combining the power of graphs with vector search to enhance information access and response relevance. The talk presents a pragmatic perspective by uncovering the various stages involved in building and using Graph RAG, and highlights some examples from recent studies that show tangible improvements when using graph retrieval in combination with vector search.

You will also learn about some ongoing open source projects in Graph RAG that can help you get started with building, experimenting, and engaging with the rapidly growing community of practitioners who are interested in this space.