You’ve heard good data matters in Machine Learning, but does it matter for Generative AI applications? Corporate data often differs significantly from the general Internet data used to train most foundation models. Join me for a demo building a customizable RAG (Retrieval Augmented Generation) stack using OSS HuggingFace embedding models, fine tuning using PyTorch, retrieval using Milvus vector database, evaluation using Ragas, and optional Zilliz cloud and OpenAI.