StackMap
Subscribe
Explore / lift
datalab-to

lift

Datalab's 9B vision model that extracts JSON matching your schema from PDFs and images in one pass — schema-constrained decoding, multi-page values, vLLM or HF inference, Schema Studio.

1,183 110 Python Apache-2.0updated 6 days ago
ocrdata
View on GitHubDispute this mapping →
Curator's take

Use it when you need fields, not Markdown — invoices, contracts, filings into a fixed JSON schema — locally: 90% field accuracy on its own 225-doc benchmark at ~3x Gemini Flash's speed on one GPU. Read the license first: commercial self-hosting needs a paid Datalab license. Keep schemas simple (no enum, oneOf or $ref, or the decoder guarantee weakens), and expect whole-document perfection only ~1 time in 5.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside lift. Ranked by curator confidence.

pairs wellalternativealternativebuilt withmarkercontextgemunstractvLLMlift
pairs wellalternativebuilt withpick a node for the why · open it from the panel
Weekly digest
README.md2 min read

Datalab Logo

Datalab

State of the Art models for Document Intelligence

Code License Model License Discord

Homepage Docs Public Playground

lift

lift extracts structured JSON from PDFs and images by passing a schema. It's a 9B vision model that returns a JSON object matching your schema, with schema-constrained decoding guaranteeing valid output.

lift extracting schema-aligned JSON from an invoice Extraction accuracy benchmark

Try lift on Datalab

Our managed platform runs improved extraction with higher accuracy than the open weights, plus per-field verification, citations, and confidence scores.

If you have high volume workloads, we offer a batch processing service that has processed 1B+ pages per week.

Get started with $20 in free credits per month — sign up - takes under 30 seconds - or try lift in our public playground.

Commercial self-hosting requires a license — see Commercial usage. For on-prem licensing, contact us.

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

The easiest way to start is with the CLI tools:

pip install lift-pdf

# With vLLM (recommended, lightweight install)
lift_vllm
lift_extract input.pdf ./output --schema schema.json

# With HuggingFace (requires torch)
pip install lift-pdf[hf]
lift_extract input.pdf ./output --schema schema.json --method hf

Benchmarks

Evaluated on a 225-document extraction benchmark (6–64 pages per document, ~11,000 scored fields) with adversarial cases planted throughout: cross-page values, exhaustive lists, fields that must be left null, near-miss distractors, multi-source aggregation. Scoring is deterministic exact-match against ground truth (numeric tolerance, normalized strings).

All models receive the same rendered page images, and extract each document in a single pass.

Model Size Field accuracy Full-document accuracy Median latency* Features
Datalab API — 95.9% 44.4% 30.8s Citations + Verification
Gemini Flash 3.5 — 91.3% 40.0% 28.1s
lift 9B 90.2% 20.9% 9.5s
Azure Content Understanding