Exercise 03 - Implement contextual grounding using vector search in Azure Cosmos DB for NoSQL

Scenario

Vector search provides a powerful technique for efficiently finding information within blocks of text. Using Azure Cosmos DB, vector embeddings generated using Azure OpenAI can be stored alongside data. In this exercise, you will add vector search capabilities to Azure Cosmos DB for NoSQL and perform similarity searches using the vectorized data.

Objectives

After you complete this lab, you will be able to:

• Enable the Vector Search feature in Azure Cosmos DB for NoSQL
• Define container vector policies
• Specify vector indexing policies
• Generate vector embeddings using Azure OpenAI and store them into Cosmos DB
• Perform similarity searches using the VectorDistance() function in Cosmos DB

Duration

• Estimated Time: 85 minutes

---

Table of contents

• 1. Enable vector search in Azure Cosmos DB for NoSQL
• 2. Create and store vector embeddings
• 3. Integrate vector search capabilities into the Contoso Suites CIS