IDUG NA 2025

Have you ever tried to use an LLM? How exactly can they be used in a business environment? And how can Db2 help with the accuracy of what an LLM produces?
This lab will take you through the various components that are used to create a system that generates a RAG (Retrieval–Augmented Generation) for an LLM to use to answer a question. You will get a chance to experiment with a system that provides a environment where you can try out different prompts and settings to see how an LLM will respond to your question. 
You will also get to see how Db2 fits into this picture and what vector calculations (and Vector databases) do when generating a RAG prompt.