Pick an embedding model that supports binary quantization and then use a SIMD-optimized Hamming Distance function. I'm doing this for Scour and doing about 1.6 billion comparisons per second.

https://scour.ing

https://emschwartz.me/binary-vector-embeddings-are-so-cool/

Depending on how 'one-off' the query is, sequential read is the right answer. The alternative is indexing the data for ANN, which will generally require doing the equivalent of many queries across the dataset.

On the bright side, smart folks have already thought pretty hard about this. In my work, I ended up picking usearch for large-scale vector storage and ANN search. It's plenty fast and is happy working with vectors on disk - solutions which are /purely/ concerned with latency often don't include support for vectors on disk, which forces you into using a hell of a lot of RAM.

https://github.com/unum-cloud/USearch

As it always happens, people realize there is something new is Redis in 2 years or more. With Streams it tragically took like 4 years and then everybody started to use it for this use case, with a sharp acceleration in the latest few years. I believe this is what is happening for vector sets as well. For a reduced size problem like that you just git clone Redis, add the vectors into a key with VADD, and query with VSIM. It's a 10 lines Python script that will deliver 20k/50k queries per second more or less, out of the box with zero optimizations.

But here the problem is: the scale. Billions of vectors. And I wonder if Redis should add on-disk vector sets, which I started to sketch months ago and never implemented. So my question is, the "3B" in Vicky's blog post is theoretical or is a practical need many folks have? I'm asking because at such a scale, the main problem is to generate the embeddings for your items, whatever they are.

https://gist.github.com/antirez/b3cc9af4db69b04756606ad91cab...

EDIT: I wonder if it is possible to use in memory vector sets to index discrete on disk dense blobs of nearby vectors to query with an approach like the one described in the post. It's like a H-HNSW, and resembles to certain on-disk approaches for vector similarity indeed.

I’m confused: I thought the original question was about doing a search for nearest neighbours. You don’t need to store the results of each comparison, just track the closest found so far?

Or just use a vector store like LanceDB or Turbopuffer and be done with it.

Using something like duckdb could help in scenarios like this one?

There is no reason to do it on a CPU instead of a GPU. Anyway, a vector database would be a better solution, although not without downsides.