Live data from Hacker News

Zvec: A lightweight, fast, in-process vector database

github.com

1–10 of 50 posts

Re: Zvec: A lightweight, fast, in-process vector database

#4
post #3

Are these sort of similarity searches useful for classifying text?

It altogether depends on the quality and suitability of the provided embedding vector that you provide. Even with a long embedding vector using a recent model, my estimation is that the classification will be better than random but not too accurate. You would typically do better by asking a large model directly for a classification. The good thing is that it is often easy to create a small human labeled dataset and estimate the error confusion matrix via each approach.

Re: Zvec: A lightweight, fast, in-process vector database

#5
post #3

Are these sort of similarity searches useful for classifying text?

Embeddings are good at partitioning document stores at a coarse grained level, and they can be very useful for documents where there's a lot of keyword overlap and the semantic differentiation is distributed. They're definitely not a good primary recall mechanism, and they often don't even fully pull weight for their cost in hybrid setups, so it's worth doing evals for your specific use case.

Re: Zvec: A lightweight, fast, in-process vector database

#8
Their self-reported benchmarks have them out-performing pinecone by 7x in queries-per-second: https://zvec.org/en/docs/benchmarks/

I'd love to see those results independently verified, and I'd also love a good explanation of how they're getting such great performance.

Re: Zvec: A lightweight, fast, in-process vector database

#10
post #3

Are these sort of similarity searches useful for classifying text?

Yes, also for semantic indexes, I use one for person/role/org matches. So that CEO == chief executive ~= managing director good when you have grey data and multiple look up data sources that use different terms.
Post reply on HN