Hacker News new | ask | show | jobs
by throwaway81523 824 days ago
Any info about how it works? I'm more interested in the the technology than in using the product. Is there a query limit for the free API though? I do have a couple of ideas.
1 comments

yup, we designed an ensemble that considers both lexical & semantic similarity and trained on large datasets of labeled text. also building data pipelines to prevent models going stale.

max 20 docs per request for free api. no official max doc length but recently had issues with large (think book length) docs.