Retrieval Augmented Generation (RAG) Walk Through Lab

This lab aims to provide a high-level understanding of how RAG works and then enable the user to perform real-time queries of a Large Language Model (LLM) both with and without RAG to see how using an LLM with external data via RAG, can be a tremendous benefit to an organization.

• Lab Architecture, What is RAG, explanation of concepts, key terms, and technologies.
• Performing an LLM query without using RAG.
• Performing an LLM query using RAG.
• Using an Agent to query an LLM using RAG.

- Windows 11 Jumpbox

- Ollama LLM Server running Llama3-8B using Nvidia L40S provided by RunAI in AI Proving Ground

- AnythingLLM

- LanceDB for Vector DB