Category: Vectors

Chad Callihan demonstrates a vector comparison:

Vectors consist of an ordered list of numbers that represent characteristics or meaning captured from data. That data could be words, images, or other files. An AI embedding model is used to analyze the data and translate it into a long list of numbers that becomes that data’s vector embedding. The closer the vector embeddings are to each other, the more closely related the meanings of the data are together.

While vectors are more commonly hundreds or thousands of numbers, we’re going to simplify it and make up three numbers for our example.

Click through for that comparison.

Mala Mahadevan continues a series on vector search:

At this point, the consideration becomes – ‘What if the graph and all of its vectors don’t fit in memory?’

If every step of graph traversal had to wait for an arbitrary SSD read, the navigation could become painfully slow.

This is the plus and the minus of an index like HNSW. If you can fit everything into memory, it’s faster than DiskANN. Once you start paging in and out of disk, DiskANN becomes considerably faster.

Greg Low continues a series on vector data in SQL Server

:In this article, I’ll explain how to implement vector search in SQL Server using the VECTOR_DISTANCE and VECTOR_SEARCH functions. You’ll learn how vector indexes work, when to use them, and what the key trade-offs are — including the current read-only table limitation. I’ll also cover the latest syntax changes in Azure SQL Database, where that limitation has already been lifted.

Click through to learn more.

Greg Low continues a series on local text embeddings:

In the first article of this series, I explained how to install and configure Ollama to host text embeddings models locally. I also demonstrated how to install Caddy as a proxy to allow SQL Server to use Ollama via https-based calls. In this article, I’ll show you how to make use of this at the SQL Server end.

Greg mentions a few embedding models, but the one I’m pushing right now is Microsoft Research’s Harrier OSS v1 model, specifically the 600m parameter version. It does extremely well in the MTEB leaderboards (the 27b variant is at the top of the board as of June 2026) and has a permissive license. It generates vectors in 1024 dimensions, so the embeddings are a bit chunky, taking up 4kb apiece. But the results are really good.

Greg Low has a demo:

Instead of working directly with text, images, or other rich content, an embedding represents that content as a set of numbers that capture semantic relationships learned by a model. This lets systems work with meaning in a mathematical way rather than relying on concepts like text matching.

Embeddings are the output of trained text-based AI models. One possibly surprising concept is that they’re used for similarity, as opposed to facts – and for relative closeness instead of exact matches.

SQL Server is not designed to host or execute those models. This isn’t a limitation; it is a design choice. While it would be possible to run code within SQL Server to generate embeddings, it just wouldn’t be a good idea.

Note that SQL Server can already run machine learning models directly, and use the PREDICT statement to make predictions. We don’t want to be doing that with the language models we need for embeddings, though.

There are also some really good local embedding models, and between that and the vector similarity functionality in SQL Server, you can perform semantic search without needing to reach out to an online service.

Andrew Pruski does a bit of math:

Here we are using cosine as a distance metric, but there are three available to us in SQL Server: –

• Euclidean Distance
• Negative Dot Product
• Cosine Distance

In this post we’ll run through all three, see how they are calculated, and explore how they differ from each other.

Click through for a description of each.