You Probably Don't Need a Vector Database
Introduction Conversations about RAG almost always start with a vector database. This article suggests you dig deeper before implementing one.
2026-06-19
1,355 reads
Introduction Conversations about RAG almost always start with a vector database. This article suggests you dig deeper before implementing one.
2026-06-19
1,355 reads
This article shows how you can generate embeddings in SQL Server 2025, store them, and use them in your queries.
2026-06-08
3,209 reads
Learn about using SQL Server to support AI-enhanced search queries with the Relational Embedding Retrieval Pattern (RERP).
2026-04-24
2,049 reads
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 […]
2026-03-23
10,388 reads
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 […]
2025-01-17
4,193 reads
By Steve Jones
I use ConEmu for my terminal interface. I’m still on Windows 10 at home,...
Creating a Fabric workspace takes about 30 seconds. Restructuring workspaces after people have built...
By Steve Jones
It’s a small change, but a handy one. Flyway Desktop (FWD) now includes the...
Comments posted to this topic are about the item Adding new column with DEFAULT...
Comments posted to this topic are about the item Advanced Deployment Scenarios: Stairway to...
Comments posted to this topic are about the item You Need a DBA Pipeline
Which number did the two COUNT(*) return:
DROP TABLE IF EXISTS #tmp CREATE TABLE #tmp (id INT NOT NULL) INSERT INTO #tmp (id) SELECT gs.value FROM GENERATE_SERIES(1, 5) AS gs ALTER TABLE #tmp ADD my_value INT NOT NULL CONSTRAINT df_tmp_my_value DEFAULT 1 SELECT COUNT(*) FROM #tmp AS t WHERE my_value = 1 ALTER TABLE #tmp DROP CONSTRAINT df_tmp_my_value ALTER TABLE #tmp ADD CONSTRAINT df_tmp_my_value DEFAULT 2 FOR my_value SELECT COUNT(*) FROM #tmp AS t WHERE my_value = 1See possible answers