Introducing lift: open-weights structured extraction (opens in new tab)

Introducing lift: open-weights structured extraction lift is a 9B open-weights vision model that extracts structured JSON from PDFs and images by passing a schema. It scores 90.2% field accuracy on our 225-document extraction benchmark - the best small self-hostable model we've tested. Table of contents Try Datalab Spin up a pipeline in minutes, or talk to sales about your use case. We’re releasing lift, a 9B open-weights vision model that extracts structured JSON from PDFs and images. You gi...