Power AI apps and develop rich experiences with Azure SQL Database
summary
Azure SQL Database claims direct support for RAG and vector workflows by integrating Azure AI Search and Azure OpenAI, and demos show it actually works: a low‑code index builds embeddings, Azure OpenAI does hybrid search, and a chat UI returns tailored answers. Engine features include native JSON, RegEx and vector functions (private preview) plus sp_invoke_rest_endpoint to call models. A proof‑of‑concept fine‑tunes Phi‑3 on SQL docs and a demo queries 200K businesses and 8M reviews with geospatial, regex, JSON and cosine similarity in seconds.
AI-written summary · about
chapters (7)
- 0:00Building Gen AI apps with Azure SQL
- 9:28Why build Gen AI apps with SQL data
- 19:27RAG apps with Azure AI Search and SQL
- 25:26Vector search and hybrid queries
- 33:16Fine-tuning LLMs with SQL data
- 39:25Copilot for Azure SQL demos
- 45:02Resources for AI with SQL
related talks
01h 16mAzure SQL ❤️ Open AI
50mBuilding AI ready applications
44mSupercharge your data with Azure AI Search and OpenAI
50mHow to design and build AI applications with vector search using Azure OpenAI & Azure Cosmos DB
30mAI: Empowering us all
56mDeveloping AI Applications with SQL AI: Ground to Cloud to Fabric
27m6 things you can do with azure_ai & PostgreSQL on Azure
12mBuilding Generative AI Apps with Azure Cosmos DB