Retrieval Augmented Generation with LangChain: ChatGPT for Your Data - Part 1

Explore the fundamentals of Retrieval Augmented Generation (RAG) in this comprehensive workshop presented by Greg Loughnane and Chris Alexiuk from AI Makerspace. Dive into the world of "ChatGPT for your private data" and learn how to build question-answering tools that deliver coherent, fact-checked responses. Discover the inner workings of RAG systems, including vector stores, embedding models, and LLMs, all integrated using LLM Ops infrastructure. Gain hands-on experience with LangChain tooling, embedding documents using a leading model, storing data in a Pinecone vector database, and leveraging Llama 2 for augmented prompts. Acquire practical skills in evaluating RAG systems and implementing emerging best practices to optimize output quality. Access all demo code via GitHub and/or Colab to jumpstart your own RAG projects.