Vectors & AI: The Twin Engines of SQL Server 2025

Proposed session for SQLBits 2026

TL; DR

Discover how SQL Server 2025 transforms data querying by combining native vector support with deep AI model integration. This session shows how semantic search goes beyond keywords, enabling meaning-based queries and more relevant results through vector similarity. Learn how to invoke large language models directly from SQL Server to enrich queries with AI-driven context, summaries, and insights—securely and efficiently. With simplified development compared to earlier Azure SQL approaches, SQL Server 2025 empowers developers and data professionals to seamlessly blend vectors and AI in a single, powerful query experience.

Session Details

Unlock the full potential of SQL Server 2025 as it brings together vector support and AI model integration to revolutionize how you query and understand your data. In this session, you’ll discover how vectors enable semantic understanding—moving beyond traditional text search to interpret the meaning of your queries and retrieve truly relevant results.

We’ll explore the enhanced AI model integration, making it easier than ever to call large language models directly from SQL Server, contextualize query results, and enrich your applications with intelligence—without compromising security. Learn how the latest improvements simplify development compared to previous Azure SQL features, while giving you the power to combine vector similarity and LLM-driven insights in a single query.

Whether you want to perform semantic search, generate AI-assisted summaries, or contextualize analytics, this session shows you how SQL Server 2025 makes advanced AI and vector operations fast, secure, and developer-friendly.

3 things you'll get out of this session

- Understand vector search and LLMs in relational databases - Understand the new SQL Server features to enable this solution - Understand possible scenarios using these AI features