DocParse - AI-Powered Document Parser API

Professional Django REST API for extracting structured information from documents (PDF, Word, Images) using AI and natural language prompts - Simple Upload & Extract!

🚀 Live Demo

Production API: https://docparse.onrender.com

• 🌐 API Endpoint: https://docparse.onrender.com/api/documents/
• 📖 Swagger UI: https://docparse.onrender.com/swagger/
• 📚 ReDoc: https://docparse.onrender.com/redoc/
• ❤️ Health Check: https://docparse.onrender.com/health/

🚀 Features

• 📄 Multi-format Support: PDF, Word (.docx), Text (.txt), and image files (JPG, PNG, etc.)
• 🤖 AI-Powered Extraction: Uses OpenAI GPT with natural language prompts
• ⚡ Instant Results: Upload document with optional prompt and get immediate extraction
• 📋 No Complex Workflows: Single endpoint - upload and extract in one step
• 🔄 RESTful API: Built with Django REST Framework
• 📚 Interactive Documentation: Swagger UI and ReDoc
• 🐳 Docker Ready: Complete containerization support
• 🔍 OCR Support: Extract text from images using Tesseract

📋 Table of Contents

• Quick Start
• Simple Usage
• API Endpoint
• Example Extractions
• Documentation
• Docker Commands
• Environment Setup

🚀 Quick Start

Using Docker (Recommended)

1. Clone and configure:

git clone <repository-url>
cd DocParse
cp .env.example .env
# Edit .env file with your OpenAI API key

2. Build and run:

docker-compose up --build

3. Access the application:

• 🌐 API: http://localhost:8000/api/documents/
• 📖 Swagger UI: http://localhost:8000/swagger/
• 📚 ReDoc: http://localhost:8000/redoc/

Manual Installation

1. Install dependencies:

pip install -r requirements.txt
sudo apt-get install tesseract-ocr  # For OCR support

2. Configure environment:

cp .env.example .env
# Edit .env file with your OpenAI API key

3. Setup database:

python manage.py makemigrations
python manage.py migrate

4. Run server:

python manage.py runserver

⚡ Simple Usage

Production API (Live)

With specific prompt:

curl -X POST https://docparse.onrender.com/api/documents/ \
  -F "file=@your_document.pdf" \
  -F "prompt=What is the total amount?"

Without prompt (extracts everything):

curl -X POST https://docparse.onrender.com/api/documents/ \
  -F "file=@your_document.pdf"

Local Development

Upload Document & Extract Information:

With specific prompt:

curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@your_document.pdf" \
  -F "prompt=What is the total amount?"

Without prompt (extracts everything):

curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@your_document.pdf"

Example Response:

{
  "seller": {
    "company_name": "BrightLine Traders Ltd",
    "address": "78 Innovation Road, Kigali, Rwanda"
  },
  "buyer": {
    "company_name": "TechNova Solutions",
    "address": "902 Enterprise Drive, Kigali, Rwanda"
  },
  "invoice_number": "PRO-2024-014",
  "date": "2024-02-10",
  "subtotal": "RWF 555,000",
  "tax": "18%",
  "total": "RWF 654,900"
}

🔗 API Endpoint

Method	Endpoint	Description
POST	/api/documents/	Upload document & extract with optional prompt

Request Parameters

Parameter	Type	Required	Description
file	File	✅	Document file (PDF, DOCX, TXT, JPG, PNG, etc.)
prompt	String	❌	Natural language question about the document
document_type	String	❌	invoice, proforma, receipt, other

💡 Example Extractions

Specific Information

# Extract total amount only
curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@invoice.pdf" \
  -F "prompt=What is the total amount?"

# Extract names only
curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@invoice.pdf" \
  -F "prompt=Get me the names of people in this document"

# Extract invoice date
curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@invoice.pdf" \
  -F "prompt=What is the invoice date?"

All Information

# Extract everything (no prompt)
curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@invoice.pdf"

Business Cards

# Extract contact info
curl -X POST http://localhost:8000/api/documents/ \
  -F "file=@business_card.jpg" \
  -F "prompt=Extract name, phone number, email, and company"

📚 Documentation

Live API Documentation

• Production Swagger: https://docparse.onrender.com/swagger/ - Test APIs directly
• Production ReDoc: https://docparse.onrender.com/redoc/ - Clean documentation

Local API Documentation

• Swagger UI: http://localhost:8000/swagger/ - Test APIs directly in browser
• ReDoc: http://localhost:8000/redoc/ - Clean, readable documentation
• OpenAPI JSON: http://localhost:8000/swagger.json - Raw API specification

Testing Tools

• Postman Collection: Import DocParse_API.postman_collection.json
  • Production URL: https://docparse.onrender.com
  • Local URL: http://localhost:8000

🐳 Docker Commands

# Start services
docker-compose up -d

# View logs
docker-compose logs -f web

# Stop services
docker-compose down

# Clean restart (if having issues)
docker-compose down -v
docker system prune -f
docker-compose up --build

⚙️ Environment Setup

Required Environment Variables

Create a .env file in the project root (copy from .env.example):

# Django Configuration
SECRET_KEY=your-secret-key-here-change-in-production
DEBUG=False
ALLOWED_HOSTS=localhost,127.0.0.1

# OpenAI Configuration (required for AI extraction)
OPENAI_API_KEY=sk-proj-your-openai-api-key-here
OPENAI_MODEL=gpt-3.5-turbo

Supported File Formats

Input Files:

• PDF: .pdf
• Word: .docx, .doc
• Text: .txt
• Images: .jpg, .jpeg, .png, .gif, .bmp, .tiff

🔧 Advanced Usage

Python Integration

import requests

# Production API
url = 'https://docparse.onrender.com/api/documents/'

# Upload and extract with specific prompt
with open('invoice.pdf', 'rb') as f:
    response = requests.post(
        url,
        files={'file': f},
        data={'prompt': 'What is the total amount?'}
    )

result = response.json()
print(f"Extracted data: {result}")

# Upload and extract everything (no prompt)
with open('invoice.pdf', 'rb') as f:
    response = requests.post(
        url,
        files={'file': f}
    )

result = response.json()
print(f"All data: {result}")

JavaScript/Node.js Integration

const FormData = require('form-data');
const fs = require('fs');

const form = new FormData();
form.append('file', fs.createReadStream('invoice.pdf'));
form.append('prompt', 'What is the total amount?');

fetch('https://docparse.onrender.com/api/documents/', {
    method: 'POST',
    body: form
})
.then(response => response.json())
.then(data => console.log(data));

🚨 Troubleshooting

Common Issues

Docker ContainerConfig error:

# Clean up Docker containers and volumes
docker-compose down -v
docker system prune -f
docker-compose up --build

OpenAI API errors:

• Check API key validity and quota
• Ensure OPENAI_API_KEY is set in .env file
• Verify you have credits in your OpenAI account

Performance Tips

• Use specific prompts for faster, more accurate results
• Optimize image quality for better OCR results
• Use PDF format when possible for best accuracy

📊 What DocParse Can Extract

With Specific Prompts:

• Any information you ask for in natural language
• Financial data (amounts, totals, line items)
• Contact information (names, emails, phones)
• Dates and reference numbers
• Custom business data

Without Prompt (Extracts All):

• All dates found in document
• All monetary amounts
• All person names
• All company names
• All email addresses

📞 Support

• 📧 Email: manziosee3@gmail.com
• 🌐 Live API: https://docparse.onrender.com
• 📖 Documentation: https://docparse.onrender.com/swagger/

🎯 Example Prompts

Get inspired with these example prompts:

• "What is the total amount?"
• "Get me the names of people in this document"
• "What is the invoice date?"
• "Extract all contact information"
• "What are the line items?"
• "Find all monetary amounts"
• "Who are the companies mentioned?"
• "What are the key dates?"
• "Extract email addresses"

Or leave prompt empty to extract everything automatically!

Simple and powerful - just upload your document and get instant results!