Welcome#
Retrieval Augmented Generation (RAG) Applications, based on Large Language Models (LLMs), are a new breed of application. The architecture has become increasingly important and is currently at the core of many engagements.
Goal#
During this workshop, we will leverage each other’s knowledge and will look at:
Pre-production: how to experiment, evaluate and come up with the best RAG-based solution for a given use case.
Post-production: after deploying the solution to production, how to monitor and ensure that it works as expected. Oh wait, what does that even mean?
Through this workshop, we aim to:
speed up the onboarding process on this topic
provide a framework that would guide you in your thought process when building such applications
last, but not least, HAVE FUN!
Ready? Let’s start!#
