README.md

metadata

title: MinerU PDF Processor
emoji: 📄
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: false
license: apache-2.0
app_port: 7860

MinerU PDF API

A simple API for extracting text and tables from PDF documents using MinerU's magic-pdf library.

Features

• Extract text from PDF documents
• Identify and extract tables from PDFs
• Works with both regular and scanned PDFs
• Simple JSON response format

API Endpoints

Health Check

GET /health

Returns the current status of the service.

Extract PDF Content

POST /extract

Upload a PDF file to extract its text and tables.

Request

• file: The PDF file to process (multipart/form-data)

Response

JSON object containing:

• filename: Original filename
• pages: Array of pages with text and tables

Deployment

This application is deployed as a Hugging Face Space using Docker.

Local Development

To run this application locally:

1. Install the requirements:

   pip install -r requirements.txt
   

2. Run the application:

   python app.py
   

3. Access the API at http://localhost:7860

Docker

You can also build and run with Docker:

docker build -t mineru-pdf-api .
docker run -p 7860:7860 mineru-pdf-api

About

This API is built on top of MinerU and magic-pdf, a powerful PDF extraction tool.

API Documentation

Once deployed, you can access the auto-generated Swagger documentation at:

https://marcosremar2-docker-mineru.hf.space/docs

For ReDoc documentation:

https://marcosremar2-docker-mineru.hf.space/redoc