Azure Cosmos DB as Vector Database
summary
Shows three concrete ways to use Cosmos DB for embeddings and what actually works: Azure AI Search indexer for no‑code ingestion using Azure OpenAI embeddings (ada‑002), MongoDB API in Cosmos DB with LangChain for chunking and storing vectors to perform similarity searches, and Postgres + Citus + PGVector which demos loading ~1 million random vectors in under two minutes and running nearest‑neighbor queries. Includes setup commands, sample Python/psycopg usage, index creation, and notes on performance and cost tradeoffs.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 0:17Why Vectors
- 1:19Native Vector Databases
- 2:13Azure AI Search
- 2:53AI Search Journey
- 6:08Azure Cosmos DB Core
- 14:50Outro
related talks
50mHow to design and build AI applications with vector search using Azure OpenAI & Azure Cosmos DB
48mThe power of AI and Copilot for Azure Databases
03h 08mAzure Cosmos DB Conf 2025
40mUnleashing the Power of Vector Search with Azure SQL Database
17mAzure Cosmos DB in AI Workflows: From Knowledge Retrieval to Microsoft Fabric Integrations
12mThe mechanics of integrating AI and vector search into Azure Database for PostgreSQL
01h 16mAzure SQL ❤️ Open AI
27m6 things you can do with azure_ai & PostgreSQL on Azure