Customizable RAG Workflows with your Own Data

In this talk, Christy Bergman explores how to build a customizable RAG (Retrieval Augmented Generation) stack using OSS HuggingFace, Milvus vector database, LangChain, and optional Zilliz cloud and OpenAI. The presentation covers the fundamentals of RAG, challenges, and best practices for optimizing GenAI workflows with proprietary data. It includes a demo showcasing the implementation with Milvus technical documentation.