Vector search is at the core of modern AI applications, powering recommendation engines, semantic search, and image recognition. Traditionally, implementing vector-based queries required adding a dedicated vector database, introducing complexity and additional infrastructure. But with SQL Server 2025, you can now store, query, and optimize vector embeddings natively - all within your existing environment, running entirely on-premises.

Why does this matter? For organizations needing full control over their data, SQL Server 2025 enables AI-powered search without relying on external cloud services or third-party databases.

In this demo-driven session, we'll start with how REST APIs are integrated into SQL Server 2025 as they are not only a cool feature on their own but also a prequisite to integrate AI into your workloads. We’ll keep going by looking at what vectors are, why they’re essential for AI applications, and how SQL Server 2025 simplifies vector search. You'll learn how to store and query vector embeddings efficiently, explore real-world scenarios like AI-powered recommendations and intelligent search, and discover best practices for indexing and optimizing performance. Of course, we’ll also take a look on what you’ll need to get going right away in your own environment!

If you're looking for a way to integrate AI-powered search within your on-premises SQL Server - without external infrastructure - this is a session you won’t want to miss!

Ben Weissman

Ben has been working with SQL Server since SQL Server 6.5, mainly in the BI/Datawarehousing field.

He is a Microsoft Data Platform MVP, a co-author of "SQL on Kubernetes", "Azure Arc-enabled Data Services Revealed", "SQL Server Big Data Clusters" and "The Biml Book" as well as a regular speaker at national and international events. He has also published multiple Video courses at Pluralsight and other platforms.

Ben is also a co-organizer of DataGrillen, New Stars of Data and dativerse as well as a volunteer and mentor for many other Data Platform events.