Approximate Vector Search with KMeans and Azure SQL

Post Content

In this episode, we’ll see how to calculate KMeans clusters for vector data so that then it can be used to do Approximate Similarity Search. We’ll offload resource intensive processing to calculate KMeans using SciKit-Learn to a container and then we’ll do cell probing in pure T-SQL.

Chapters:
00:00 – Introduction
02:15 – Vector in SQL
04:00 – Indexing
08:40 – KMeans
11:25 – Demo

✔️Resources:
Intelligent applications with Azure SQL Database: https://aka.ms/sqlai
Azure SQL Devs’ Corner: https://devblogs.microsoft.com/azure-sql/
Vector Search Optimization via KMeans, Voronoi Cells and Inverted File Index (aka “Cell-Probing”): https://devblogs.microsoft.com/azure-sql/vector-search-optimization-via-kmeans-voronoi-cells-and-inverted-file-index-aka-cell-probing/

? Let’s connect:
Twitter – Anna Hoffman, https://twitter.com/AnalyticAnna
Twitter – AzureSQL, https://aka.ms/azuresqltw

? Watch even more Data Exposed episodes: https://aka.ms/dataexposedyt

? Subscribe to our channels for even more SQL tips:
Microsoft Azure SQL: https://aka.ms/msazuresqlyt
Microsoft SQL Server: https://aka.ms/mssqlserveryt
Microsoft Developer: https://aka.ms/microsoftdeveloperyt

#AzureSQL #SQL #LearnSQL Read More Microsoft Developer