This repository contains the code and documentation for the MongoDB User Group Toronto's session on Retrieval-Augmented Generation (RAG). Learn how to architect a RAG pipeline from scratch using Google Gemini for generation and MongoDB Atlas as a powerful vector database for semantic retrieval. The included notebook guides you through data chunking, generating vector embeddings, and performing similarity searches to ground LLM responses in real-world data. By the end of this session, you will be fully prepared to complete the MongoDB RAG Skill Badge exam and claim your Credly credential.
Follow the Step-by-Step Documentation to set up your environment, configure your MongoDB Atlas cluster, and launch the Google Colab notebook to run the code.