Vector Database

SQLServerCentral Article

Vectors in SQL Server 2025

  • Article

Introduction SQL Server 2025 introduced new features, including vectors. The main purpose of vectors is to create a new semantic search with the help of AI. Modern AI models represent text as vectors (embeddings) that capture semantic meaning. Similar meanings produce vectors that are close to each other in this vector space, allowing AI systems to […]

(3)

You rated this post out of 5. Change rating

2026-03-23

10,179 reads

SQLServerCentral Article

Vector DB implementation using FAISS

  • Article

Searching for relevant information in vast repositories of unstructured text can be a challenge. This article explains a Python-based approach to implementing an efficient document search system using FAISS (Facebook AI Similarity Search) for Vector DB and sentence embeddings, which can be useful in applications like chatbots, document retrieval, and natural language understanding. In this […]

You rated this post out of 5. Change rating

2025-01-17

4,107 reads

Blogs

Measuring RAG Solutions: Are We Retrieving the Right Information?

By

A RAG pipeline that answers questions in the demo is not the same thing...

Advice I Like: Lots of Ideas

By

“A multitude of bad ideas is necessary for one good idea” – from Excellent...

Building a DBA Agent for Your SQL Server Estate with MCP

By

Yesterday I gave a talk for MSSQLTips called “Building a DBA Agent for Your...

Read the latest Blogs

Forums

How do I connect to a SQL Server database on my ISP?

By Doctor Who 2

I've got a web application for my side business. I've added a SQL Server...

Looking for New Blood

By Grant Fritchey

Comments posted to this topic are about the item Looking for New Blood

Server-Level Row Counts for Tables and Views

By Artur Sanin

Comments posted to this topic are about the item Server-Level Row Counts for Tables...

Visit the forum

Question of the Day

Hyperscale Replicas I

What types of secondary replicas are available for the Azure SQL Database Hyperscale edition?

See possible answers