ADEO Dev x Data x PMS 2024

In this talk, we will present the main concepts of a RAG and capabilities. We will create an application from scratch using LlamaIndex.

Program:
Explains what RAG (Retrieval Augmented Generation) and what problem does it solves
Vectorize your documents and store them into a Vector Database
Build a retrieval mechanism - Generate query embedding, Vector, Keyword based, both!
Re-rank the documents that are more aligned with user queries
Evaluate your responses
Create prompts with LlamaIndex

At the end of this talk, you will be able to understand the main RAG concepts, what you can do using LLM's and of course what the limitations you can find through trying to build a RAG.