lift lift is a structured extraction model from Datalab that pulls structured JSON out of PDFs and images. Pass any JSON schema and lift returns a JSON object matching it, using schema constrained decoding to guarantee valid, well typed output. Try lift in the free playground, or use the hosted API for higher accuracy, per field verification, and citations. Features Extract structured data from documents Pass any JSON schema Handles multi page documents in a single pass, including values that span pages Two inference modes: local (HuggingFace) and remote (vLLM server) CLI for single files, inline schemas, or whole directories Schema Studio: a Streamlit app to build, save, and test schemas against your documents Quickstart A schema is standard JSON Schema. Keep it simple — string , number , integer , boolean , arrays of those, arrays of objects, and nested objects are all supported. Write a description for any field whose name isn't self explanatory, and mark a field required only when it must appear; fields genuinely absent from a document come back null . Usage With vLLM (recommended) With HuggingFace Transformers extract accepts the schema as a dict, a path to a .json file, an in…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy