One of the cornerstones of AI is a concept called embeddings. Virtually every AI model, whether for text, video, or audio, uses something related to embeddings. Starting with SQL Server 2025, this is a term you’ll be hearing a lot, as its potential for applications is enormous!
2025-03-17
CSO recently published an article based on a report from Harmonic about generative AI data leaks, and the findings were eye-opening. According to the report, over 8% of employee prompts to public large language models (LLMs) contained sensitive data, ranging from security and compliance issues to privacy and legal vulnerabilities. This wasn’t just a handful […]
2025-03-08
151 reads
Steve re-posts a question from someone else, asking why you wouldn't want to use an AI.
2025-02-26
209 reads
2025-02-24
149 reads
This article shows how to insert data into a database, create embeddings, and then use this data to search the data with a natural language interface.
2025-02-14
2,817 reads
Steve has a few thoughts on a interview with Grady Booch, an icon in our industry, who have a great quote on AI technology.
2025-02-07
105 reads
AI has tremendous possibilities but also a number of security issues. Steve highlights one scary security issue today.
2025-01-27
116 reads
Most of us don't work on budgets, but we are affected by them. Is it a good idea for IT management to use AI to help plan their budgets? Steve has a few thoughts today.
2025-01-22
101 reads
I set up a local AI LLM to run and then conducted some experiments. This post shows a bit about the experiments and a little code. The setup is on my blog using Docker to containerize an Ollama LLM, which you can read about. The Basic Setup If you read my blog, I downloaded an […]
2025-01-20
1,804 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
3,462 reads
Every organization I talk to has the same problem dressed up in different clothes....
By DataOnWheels
I am delighted to host this month’s T-SQL Tuesday invitation. If you are new...
By alevyinroc
Ten years (and a couple jobs) ago, I wrote about naming default constraints to...
Comments posted to this topic are about the item The day-to-day pressures of a...
Hello all, I’m looking for advice on how to derive a daily snapshot table...
We need to replace our Windows server running SQL 2017. Any reason not to...
I have some data in a table that looks like this:
BeerID BeerName brewer beerdescription 1 Becks Interbrew Beck's is a German-style pilsner beer 2 Fat Tire New Belgium Toasty malt, gentle sweetness, flash of fresh hop bitterness. 3 Mac n Jacks Mac & Jack's Brewery This beer erupts with a floral, hoppy taste 4 Alaskan Amber Alaskan Brewing Alaskan Brewing Amber Ale is an "alt" style beer 8 Kirin Kirin Brewing Kirin Ichiban is a Lager-type beerIf I run this, what is returned?
select t1.[key]
from openjson((select t.* FROM Beer AS t for json path)) t1 See possible answers