README.md

metadata

title: MinerU PDF Processing
emoji: 📄
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 7860
pinned: false

MinerU PDF Processor

This Space runs the MinerU PDF processing tool that can extract and analyze content from PDF documents.

Features

• PDF text extraction
• Document layout analysis
• Formula recognition
• Table detection and extraction

How to Use

1. Upload a PDF document
2. The service will process the document
3. View the extracted content including text, tables, and formulas

Configuration

This Space uses the configuration specified in magic-pdf.json. You can modify this file to change the behavior of the PDF processor.

Credits

This Space uses MinerU, an open-source PDF processing toolkit.