Given a text and a list of texts, rank the list by similarity

Hi,

Text A = “The blue car is flying”

List of texts Z contains +100,000 different text entries.

The objective is to rank list of texts Z by similarity against Text A.

Text similarity APIs are accepted.

I can have the text entries also as vector embeddings so a cosine similarity API service can be used as well.

What would you suggest?

If you know any tool that might work at smaller scale (lists of 100 entries) please share it as well.

Thanks

Good luck with that.

1 Like

Hi there, what you’re asking for is absolutely doable :). I’m developing the swiss knife API for text in low code Text Search & Manipulation for Low Code API Documentation (tareef.ramez.roustom) | RapidAPI, and I would love to add your use case to it, so could you perhaps share a sample of your data?

1 Like

Sure! I just sent you a pm

Hey @tareef.ramez.roustom, I’m looking at doing a similar thing with cosine similarity to establish semantic search from vector embeddings. Is this something you could help with? If so, I’d love to PM you too :slight_smile: