Description:

Retrieval-Augmented Generation (RAG) is an approach to build Large Language Model (LLM) based systems which are grounded on an external knowledge base, such as a collection of academic papers, clinical data, books, or websites. In research, RAG is applied to a plethora of tasks, from improving medical diagnoses, to summarizing legal documents, to generating novel research ideas grounded on well-vetted and trusted sources. In this hands-on workshop, we will start by learning the basic framework and core elements of RAG, including embedding models, vector databases, indexing techniques, and generative models. We will then build a RAG system step by step and test it on provided datasets. 

Prerequisites: Basic familiarity with Python.