LLMs are great at answering generic questions, but how do you get them to answer questions about your organization’s data? In this workshop, you will learn the foundational concepts of Retrieval Augmented Generation (RAG), including chunking, embedding, and semantic search. You will also gain hands-on experience by building an end-to-end, RAG-based chatbot using MongoDB Atlas and open-source LLMs. So, be sure to bring a laptop to get the most out of this session.
You will be provided with all the resources required to successfully execute the hands-on portions of the workshop, including a GitHub repository of Jupyter Notebook templates with pseudocode. During the workshop, you will replace the pseudocode in the templates with your code.
