Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

• UpdatedDec 16, 2025
• Python

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

• UpdatedDec 17, 2025
• Python

A Unified Toolkit for Deep Learning Based Document Image Analysis

• UpdatedAug 15, 2024
• Python

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

• UpdatedJul 25, 2025
• Jupyter Notebook

Read and extract text and other content from PDFs in C# (port of PDFBox)

• UpdatedDec 7, 2025
• C#

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

• UpdatedDec 17, 2025
• Python

OCR engine for all the languages

• UpdatedDec 13, 2025
• Python

Document Layout Analysis resources repos for development with PdfPig.

• UpdatedOct 1, 2023
• C#

A toolbox of ocr models and algorithms based on MindSpore

• UpdatedJul 24, 2025
• Python

Analysis of Chinese and English layouts 中英文版面分析

• UpdatedAug 6, 2025
• Python

📝 针对文档类图像做内容提取，将文档类图像一比一输出到Word或者Txt中，便于进一步使用或处理。后续计划支持输入PDF/图像，输出对应json格式、Txt格式、Word格式和Markdown格式。

• UpdatedNov 1, 2024
• Python

YOLO models trained by DocLayNet - power your Document Intelligent by Layout Analysis

• UpdatedAug 3, 2025
• Python

Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.

• UpdatedOct 18, 2025
• Jupyter Notebook

基于paddleOCR的nodejs库

• UpdatedAug 23, 2025
• TypeScript

An official implementation of paper "Paragraph2Graph: A Language-independent GNN-based framework for layout analysis"

• UpdatedOct 14, 2023
• Python

A Unified Toolkit for Deep Learning-Based Table Extraction

• UpdatedNov 21, 2024
• Python

Trained Detectron2 object detection models for document layout analysis based on PubLayNet dataset

• UpdatedApr 16, 2023
• Python

[ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)

• UpdatedOct 6, 2023
• Python

A keyboard layout that provides an elegant and balanced typing experience by its use of a thumb-alpha, emphasis on middle fingers, deprioritisation of pinkies, and arcane keys.

• UpdatedNov 7, 2025

A Large Dataset of Historical Japanese Documents with Complex Layouts

• UpdatedJul 22, 2022
• Jupyter Notebook