Postgres and OpenAI - a match made in Azure
summary
Shows PostgreSQL on Azure calling Azure OpenAI via the azure_ai extension to generate embeddings, then stores them with pgvector and a Microsoft research kN index to run fast approximate nearest-neighbor searches over ~30,000 Yelp reviews. Demonstrates semantic search (create_embeddings + cosine), an extractive→abstractive summarization pipeline, sentiment classification via Azure Language, and PII detection/redaction — all done from SQL without separate glue code, improving latency and operational simplicity.
AI-written summary · about
chapters (9)
- 0:00Postgres and OpenAI on Azure
- 1:14AI inside the database
- 6:23Semantic search with vectors
- 13:56Storing vector embeddings
- 20:25Demo: semantic search on Yelp
- 26:25Document summarization
- 30:24Search and summarization query
- 36:41Sentiment and PII demos
- 43:03Resources and closing
related talks
12mThe mechanics of integrating AI and vector search into Azure Database for PostgreSQL
27m6 things you can do with azure_ai & PostgreSQL on Azure
01h 16mAzure SQL ❤️ Open AI
50mBuilding AI ready applications
20mBuilding Enterprise RAG with Azure Database for PostgreSQL and pgvector
24mPostgres-powered AI: Running an End-to-End AI Platform with Postgres on Azure
46mTransform applications with AI and Azure Database for PostgreSQL
48mThe power of AI and Copilot for Azure Databases