lift-pdf

Extract structured data from PDFs and images by passing a schema.

lift-pdf is the Python package and CLI for Datalab's lift, a document extraction tool/model that extracts structured JSON from PDFs and images using a supplied JSON schema with schema-constrained decoding.

Recent stories

1 linked story

releasePRIMARY2026-06-19

lift-pdf releases 9B extractor with 90.2% accuracy and 9.5s p50

lift-pdf released an open-source 9B model for schema-constrained document extraction, with code, pip install, playground access, and a 90.2% score on the team's 225-document bench. It matters because the model claims near-Gemini 3.5 Flash accuracy at 9.5s p50, though coverage is still skewed toward Latin-language docs and commercial-use limits remain.