Build Intelligent Applications using ChatGPT and Vector Search with Data in Azure Cosmos DB

Regular 50 minute session for SQLBits 2026

TL; DR

This session shows how to build AI-powered applications by combining ChatGPT with vector search in Azure Cosmos DB. You’ll learn how vector embeddings enable efficient similarity search over your data and how integrating Azure OpenAI models allows applications to retrieve relevant context, reason over it, and generate smarter, more accurate responses for real-world scenarios such as NLP, computer vision, and intelligent search.

Session Details

Using vector embeddings, Azure Cosmos DB's vector search capability enables you to run similarity searches on data kept in your Cosmos DB container. This feature is very helpful in situations requiring computer vision, natural language processing, machine learning, and other applications where you need to locate objects that are comparable to a specified query item.
Your AI-powered apps can advance significantly with the help of the Large Language Models (LLMs) in Azure OpenAI. When LLMs have timely access to the appropriate data from your application's data store, their usefulness can rise considerably.

3 things you'll get out of this session

1. Understand how vector embeddings and vector search work in Azure Cosmos DB for similarity-based retrieval

2. Learn how to combine ChatGPT with your own data to build intelligent, context-aware applications

3. Gain practical insights into real-world AI use cases using Azure OpenAI and Cosmos DB