RAG Using Semantic Kernel with Azure OpenAI and Azure Cosmos DB - Python Data Science

Explore the integration of Retrieval Augmented Generation (RAG) using Semantic Kernel with Azure OpenAI and Azure Cosmos DB in this 30-minute conference talk. Dive into the new capabilities of Azure Cosmos DB for MongoDB vCore and Semantic Kernel, enabling vector search and AI-based application integration with data stored in Azure Cosmos DB. Learn about efficient storage, indexing, and querying of high-dimensional vector data directly in Azure Cosmos DB for MongoDB vCore. Discover how to set up Azure Cosmos DB for MongoDB vCore, deploy Azure OpenAI chat and embedding models, and understand Semantic Kernel's functionality. Follow along with a step-by-step demonstration of building a Flask application that generates responses using vector search and RAG. Gain insights from John Aziz, a Microsoft AI MVP and Gold Microsoft Learn Student Ambassador, as he guides you through the process, making it accessible for both beginners and experienced developers.

RAG using Semantic Kernel with
Agenda
Prerequisites
Microsoft Technologies used
Concepts used
Demo - RAG in Jupyter Notebooks
Resources