---
title: Extract Document To Markdown
emoji: 🌖
colorFrom: yellow
colorTo: gray
sdk: gradio
sdk_version: 5.32.1
app_file: app.py
pinned: false
license: mit
short_description: extract a document from pdf/docx to md
tags:
  - mcp-server-track
---

# Document Extraction Tool - Simplified Version

A streamlined tool that extracts text from PDF and DOCX files and converts it to Markdown format. The extractor is initialized at startup and ready to process documents on demand.

## Features

- **Fast startup** - Extractor pre-initialized and ready to use
- **PDF & DOCX support** - Extract text from common document formats  
- **Markdown output** - Clean, structured markdown format
- **Enhanced extraction** - Uses Docling when available, PyPDF2 as fallback
- **Error handling** - Graceful handling of corrupted or problematic files
- **Simple interface** - Clean, easy-to-use web interface

## Quick Start

```bash
# Install dependencies
pip install -r requirements.txt

# Run the application  
python app.py
```

Access the tool at: `http://localhost:7860`

## Usage

1. Upload a PDF or DOCX document
2. Click "Extract Text" 
3. View the extracted Markdown content
4. Download the results if needed

## Technology

- **Gradio** - Web interface
- **Docling** - Advanced document extraction (optional)
- **PyPDF2** - PDF processing fallback
- **python-docx** - DOCX processing

## Architecture

The tool uses a singleton pattern with a pre-initialized extractor:
- Faster response times (no initialization delay)
- Automatic fallback between extraction methods
- Enhanced error handling for edge cases

## License

MIT

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference