There are 15 repositories under document-understanding topic.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A Repo For Document AI
A curated list of resources for Document Understanding (DU) topic
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)
Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)
Sample applications and demos for Document AI, the end-to-end document processing platform on Google Cloud
Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.
Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.
Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.
ReadingBank: A Benchmark Dataset for Reading Order Detection
A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.
Object Detection Model for Scanned Documents
Checkbox Detection Model for Scanned Documents
Official release of RFUND introduced in the paper "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction" (arXiv:2401.03472).
TAT-DQA: Towards Complex Document Understanding By Discrete Reasoning
Implementation of the paper: Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer.
Run optical character recognition with PyTesseract from the FiftyOne App!
This small module connects Label Studio with Fonduer by creating a fonduer labeling function for gold labels from a label studio export. Documentation: https://irgroup.github.io/labelstudio-to-fonduer/
(WIP) ✨ A comprehensive resource for understanding the world of software used in the Document Understanding field. 🧙✨
A hands-on CLI tool sample showcasing the integration of Dart with Google Cloud's DocumentAI.
This project tackles a real-world challenge of automating client document processing, with a focus on enhancing document classification, error detection, data extraction, and validation.
QuickCapture Mobile Scanning SDK Specially designed for native IOS
QuickCapture Mobile Scanning SDK Specially designed for native ANDROID from Extrieve
LAISA (Local AI Search Application) is a desktop app which allows you to run completely local, private, and free LLM inference. LAISA supports basic RAG with pre-configured OpenSearch Databases, and local document parsing with PDFs.
Analysing expense reports/invoices with AWS Textract and boto3.