[noufalibrahim]

What are the good solutions in this space? Vector databases I mean. Mostly for semantic search across various texts.

I have a few projects I'd like to work on. For typical web projects, I have a "go to" stack and I'd like to add something sensible for vector based search to that.

[StrauXX]

In my experience its usually easiest to use a vector store extension for an off-the-shelf database like postgres (pgvector is nice). That way you don't have to manage another, rapidly changing, service and you can easily combine queries on the vectors with regular columns, join them and so on.

[jbellis]

JVector (the index used in TFA) is available as a service with a friendly API from DataStax. https://www.datastax.com/products/datastax-astra

[article author, I work on JVector and Astra]

[riku_iki]

Could you tell how scalable JVector is? How many vectors it can handle, like millions, billions, hundreds of billions?

[noufalibrahim]

Nice. I wanted to try something out on a machine before moving to hosted soclutions.