13 projects
datalab-python-sdk
SDK for the Datalab document intelligence API
omni-parse-bench
A document-parsing benchmark: yes/no tests on single pages, graded against a provider's outputs.
chandra-ocr
OCR model that converts documents to markdown, HTML, or JSON.
surya-ocr
OCR, layout, reading order, and table recognition in 90+ languages.
marker-pdf
Convert documents to markdown with high speed and accuracy.
omni-bench-core
The shared core of the omni benchmarks: tasks, adapters, scorers, runs and the loop over them
omni-extract-bench
One scorer for document-extraction benchmarks: leaf value accuracy with optimal row matching.
indra-ocr
Fast CPU OCR: line detection, CTC recognition, reading order and markdown, on ONNX Runtime
lift-pdf
Extract structured data from PDFs and images by passing a schema.
pdftext
Extract structured text from pdfs quickly
tabled-pdf
Detect and recognize tables in PDFs and images.
texify
OCR for latex images
streamlit-drawable-canvas-jsretry
A Streamlit custom component for a free drawing canvas using Fabric.js. A fork to enable retrying for bg images.