Unleashing the Power of Vector Search with Azure SQL Database
summary
Shows Azure SQL Database running built‑in vector search: creates a vector table with 1536‑dim embeddings, calls an external model via SP_INVOKE_EXTERNAL_REST_ENDPOINT to get embeddings, stores vectors, builds indexes and runs cosine distance queries and ANN, and wires a Python WebDriver scrape into the pipeline. Demo loads a resume PDF, computes similarities and returns ranked jobs (top result ~63% match), and the live demo mostly succeeds aside from a couple of ordinary demo hiccups.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:54SQL Server 2025 AI overview
- 7:07Vector search AI problems
- 8:31SQL Server vs PostgreSQL
- 12:28Demo: vector embeddings
- 19:41Demo: REST embeddings
- 23:19Developer features architecture
- 25:42Demo: resume matching
- 34:02Use cases and call to action
related talks
01h 16mAzure SQL ❤️ Open AI
12mThe mechanics of integrating AI and vector search into Azure Database for PostgreSQL
50mHow to design and build AI applications with vector search using Azure OpenAI & Azure Cosmos DB
15mAzure Cosmos DB as Vector Database
27m6 things you can do with azure_ai & PostgreSQL on Azure
48mThe power of AI and Copilot for Azure Databases
12mBuilding Generative AI Apps with Azure Cosmos DB
47mExtendable by Design: Building Generative AI Apps with Postgres and Vector Storage and Azure AI