LiLT

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

A Repo For Document AI

Open-source platform for extracting structured data from documents using AI.

Parsing-free RAG supported by VLMs

This repository provides train＆test code, dataset, det.&rec. annotation, evaluation script, annotation tool, and ranking.

Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)

A package for parsing PDFs and analyzing their content using LLMs.

RObust document image BINarization

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.