ltengelis

I wanted a convenient tool to both compute vector embeddings of text and also perform similarity search over them. Thus 'babyvec' - defaults to computing Jina V2 embeddings locally and persisting them via 'npy-append-array'. This tool is not yet battle-tested but has been very useful for me in experimentation. Hope you might find it useful.

Frankly I think you've said it all here - a properly designed API + a well designed LLM interface on top of that enables non-technical people to do things they otherwise couldn't.