Graph Databases, Knowledge Graphs, and Retrieval Augmented Generation - Fireside Chat with Wey Gu

​Retrieval-Augmented Generation (RAG) is a popular concept - it combines a retrieval model with an LLM, and is commonly used in implementing LLM-powered QA systems.

​Existing RAG stacks have centered around combining a vector database with an LLM. But vector databases on their own lack the ability to represent data in richer ways.

​Wey Gu (Chief Evangelist at NebulaGraph) has been leading the charge on exploring how to combine LLMs with graph databases - graph databases enable more sophisticated forms of data retrieval that exploit relationships between data.

​Join us as we give an overview of the basics of graph stores, how they can be used in RAG, and how they compare to / can be used with vector db's! We'll go over some of Wey's fantastic work bringing the power of graph stores to LlamaIndex.