Welcome to the PDF-Extract-Kit Documentation

High-Quality Document Parsing Toolkit

Star Watch Fork

Tutorial

Getting Started

• Installation
  • Best Practices
• Model Weights Download
  • [Recommended] Method 1: snapshot_download
  • Method 2: Git LFS
• Quick Start
  • Layout Detection Example
  • Formula Detection Example

Core Algorithm Modules

• Layout Detection Algorithm
  • Introduction
  • Model Usage
• Formula Detection Algorithm
  • Introduction
  • Model Usage
• Formula Recognition Algorithm
  • Introduction
  • Model Usage
• OCR (Optical Character Recognition) Algorithm
  • Introduction
  • Model Usage
• Table Recognition Algorithm
  • Introduction
  • Model Usage
• Reading Order Algorithm

Task Extensions

• Code Implementation
  • Task Definition and Registration
  • Model Definition and Registration
  • Example Script
  • Support Type Extension
  • Batch Processing Extension
• Documentation Supplement
• Model Performance Evaluation

Supported Models

• The Supported Models

Model Performance Evaluation

• Layout Detection Evaluation
• Formula Detection Evaluation
• Formula Recognition Evaluation
• OCR Evaluation
• Table Recognition Evaluation
• Reading Order Evaluation
• PDF Content Extraction Evaluation [End-to-End]

PDF Projects

• Document Content Extraction Project
  • Introduction
  • Project Usage
• Document Translation Project
• Model Acceleration Project