What's new in vector indexing for Microsoft SQL | Data Exposed
Bob Ward and Anna Hoffman walk through recent improvements to vector indexing in Microsoft SQL, including new query and indexing capabilities and what to know when using vector search features in Azure SQL Database and SQL Server.
Overview
The episode covers updates to vector indexing for Microsoft SQL, including performance-related improvements and a demo showing how to create and query a vector index.
Chapters (from the video description)
- 0:00 Context on vector indexing for Microsoft SQL
- 1:10 What's new
- 1:40 Iterative filtering
- 2:00 Demo starts
- 2:15 Named replicas in Azure SQL Database Hyperscale
- 2:30 Steps to create vector index
- 4:00
TOP WITH APPROXIMATE - 5:00 What else you should know
- 5:32 How much faster it is
- 6:20 New certification: DP-800
- 6:45 SQL AI in a Day: https://aka.ms/sqlaiad
Resources
- Microsoft Learn: https://learn.microsoft.com/sql/sql-server/ai/vectors?view=sql-server-ver17
- Sample repo: https://github.com/Azure-Samples/azure-sql-db-vector-search
- Slide decks: https://aka.ms/mssqldecks
People and channels mentioned
- Anna Hoffman (Twitter): https://twitter.com/AnalyticAnna
- AzureSQL (Twitter): https://aka.ms/azuresqltw
- Data Exposed playlist: https://aka.ms/dataexposedyt
- Microsoft Azure SQL channel: https://aka.ms/msazuresqlyt
- Microsoft SQL Server channel: https://aka.ms/mssqlserveryt
- Microsoft Developer channel: https://aka.ms/microsoftdeveloperyt