📄 Document Translation API

A powerful SaaS-ready Python API for translating complex structured documents (Excel, Word, PowerPoint) while strictly preserving the original formatting, layout, and embedded media.

✨ Features

🔄 Multiple Translation Providers

Provider	Type	Description
Google Translate	Cloud	Free, fast, reliable
Ollama	Local LLM	Privacy-focused, customizable with system prompts
WebLLM	Browser	Runs entirely in browser using WebGPU
DeepL	Cloud	High-quality translations (API key required)
LibreTranslate	Self-hosted	Open-source alternative
OpenAI	Cloud	GPT-4o/4o-mini with vision support

📊 Excel Translation (.xlsx)

• ✅ Translates all cell content and sheet names
• ✅ Preserves cell merging, formulas, and styles
• ✅ Maintains font styles, colors, and borders
• ✅ Image text extraction with vision models
• ✅ Adds translated image text as comments

📝 Word Translation (.docx)

• ✅ Translates body text, headers, footers, and tables
• ✅ Preserves heading styles and paragraph formatting
• ✅ Maintains lists, images, charts, and SmartArt
• ✅ Image text extraction and translation

📽️ PowerPoint Translation (.pptx)

• ✅ Translates slide titles, body text, and speaker notes
• ✅ Preserves slide layouts, transitions, and animations
• ✅ Image text extraction with text boxes added below images
• ✅ Keeps layering order and positions

🧠 LLM Features (Ollama/WebLLM/OpenAI)

• ✅ Custom System Prompts: Provide context for better translations
• ✅ Technical Glossary: Define term mappings (e.g., batterie=coil)
• ✅ Presets: HVAC, IT, Legal, Medical terminology
• ✅ Vision Models: Translate text within images (gemma3, qwen3-vl, gpt-4o)

🏢 SaaS-Ready Features

• 🚦 Rate Limiting: Per-client IP with token bucket and sliding window algorithms
• 🔒 Security Headers: CSP, XSS protection, HSTS support
• 🧹 Auto Cleanup: Automatic file cleanup with TTL tracking
• 📊 Monitoring: Health checks, metrics, and system status
• 🔐 Admin Dashboard: Secure admin panel with authentication
• 📝 Request Logging: Structured logging with unique request IDs

🚀 Quick Start

Installation

# Clone the repository
git clone https://gitea.parsanet.org/sepehr/office_translator.git
cd office_translator

# Create virtual environment
python -m venv venv
.\venv\Scripts\Activate.ps1

# Install dependencies
pip install -r requirements.txt

# Run the API
python main.py

The API starts on http://localhost:8000

Frontend Setup

cd frontend
npm install
npm run dev

Frontend runs on http://localhost:3000

📚 API Documentation

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

🔧 API Endpoints

Translation

POST /translate

Translate a document with full customization.

curl -X POST "http://localhost:8000/translate" \
  -F "file=@document.xlsx" \
  -F "target_language=en" \
  -F "provider=ollama" \
  -F "ollama_model=gemma3:12b" \
  -F "translate_images=true" \
  -F "system_prompt=You are translating HVAC documents."

Monitoring

GET /health

Comprehensive health check with system status.

{
  "status": "healthy",
  "translation_service": "google",
  "memory": {"system_percent": 34.1, "system_available_gb": 61.7},
  "disk": {"total_files": 0, "total_size_mb": 0},
  "cleanup_service": {"is_running": true}
}

GET /metrics

System metrics and statistics.

GET /rate-limit/status

Current rate limit status for the requesting client.

Admin Endpoints (Authentication Required)

POST /admin/login

Login to admin dashboard.

curl -X POST "http://localhost:8000/admin/login" \
  -F "username=admin" \
  -F "password=your_password"

Response:

{
  "status": "success",
  "token": "your_bearer_token",
  "expires_in": 86400
}

GET /admin/dashboard

Get comprehensive dashboard data (requires Bearer token).

curl "http://localhost:8000/admin/dashboard" \
  -H "Authorization: Bearer your_token"

POST /admin/cleanup/trigger

Manually trigger file cleanup.

GET /admin/files/tracked

List currently tracked files.

🌐 Supported Languages

Code	Language	Code	Language
en	English	fr	French
fa	Persian/Farsi	es	Spanish
de	German	it	Italian
pt	Portuguese	ru	Russian
zh	Chinese	ja	Japanese
ko	Korean	ar	Arabic

⚙️ Configuration

Environment Variables (.env)

# ============== Translation Services ==============
TRANSLATION_SERVICE=google
DEEPL_API_KEY=your_deepl_api_key_here

# Ollama Configuration
OLLAMA_BASE_URL=http://localhost:11434
OLLAMA_MODEL=llama3
OLLAMA_VISION_MODEL=llava

# ============== File Limits ==============
MAX_FILE_SIZE_MB=50

# ============== Rate Limiting (SaaS) ==============
RATE_LIMIT_ENABLED=true
RATE_LIMIT_PER_MINUTE=30
RATE_LIMIT_PER_HOUR=200
TRANSLATIONS_PER_MINUTE=10
TRANSLATIONS_PER_HOUR=50
MAX_CONCURRENT_TRANSLATIONS=5

# ============== Cleanup Service ==============
CLEANUP_ENABLED=true
CLEANUP_INTERVAL_MINUTES=15
FILE_TTL_MINUTES=60
INPUT_FILE_TTL_MINUTES=30
OUTPUT_FILE_TTL_MINUTES=120

# ============== Security ==============
ENABLE_HSTS=false
CORS_ORIGINS=*

# ============== Admin Authentication ==============
ADMIN_USERNAME=admin
ADMIN_PASSWORD=changeme123  # Change in production!
# Or use a SHA256 hash:
# ADMIN_PASSWORD_HASH=your_sha256_hash

# ============== Monitoring ==============
LOG_LEVEL=INFO
ENABLE_REQUEST_LOGGING=true
MAX_MEMORY_PERCENT=80

Ollama Setup

# Install Ollama (Windows)
winget install Ollama.Ollama

# Pull a model
ollama pull llama3.2

# For vision/image translation
ollama pull gemma3:12b
# or
ollama pull qwen3-vl:8b

🎯 Using System Prompts & Glossary

Example: HVAC Translation

System Prompt:

You are translating HVAC technical documents.
Use precise technical terminology.
Keep unit measurements (kW, m³/h, Pa) unchanged.

Glossary:

batterie=coil
groupe froid=chiller
CTA=AHU (Air Handling Unit)
échangeur=heat exchanger
vanne 3 voies=3-way valve

Presets Available

• 🔧 HVAC: Heating, Ventilation, Air Conditioning
• 💻 IT: Software and technology
• ⚖️ Legal: Legal documents
• 🏥 Medical: Healthcare terminology

<EFBFBD> Admin Dashboard

Access the admin dashboard at /admin in the frontend. Features:

• System Status: Health, uptime, and issues
• Memory & Disk Monitoring: Real-time usage stats
• Translation Statistics: Total translations, success rate
• Rate Limit Management: View active clients and limits
• Cleanup Service: Monitor and trigger manual cleanup

Default Credentials

• Username: admin
• Password: changeme123

⚠️ Change the default password in production!

🏗️ Project Structure

Translate/
├── main.py                      # FastAPI application with SaaS features
├── config.py                    # Configuration with SaaS settings
├── requirements.txt             # Dependencies
├── mcp_server.py               # MCP server implementation
├── middleware/                  # SaaS middleware
│   ├── __init__.py
│   ├── rate_limiting.py        # Rate limiting with token bucket
│   ├── validation.py           # Input validation
│   ├── security.py             # Security headers & logging
│   └── cleanup.py              # Auto cleanup service
├── services/
│   └── translation_service.py  # Translation providers
├── translators/
│   ├── excel_translator.py     # Excel with image support
│   ├── word_translator.py      # Word with image support
│   └── pptx_translator.py      # PowerPoint with image support
├── frontend/                    # Next.js frontend
│   ├── src/
│   │   ├── app/
│   │   │   ├── page.tsx        # Main translation page
│   │   │   ├── admin/          # Admin dashboard
│   │   │   └── settings/       # Settings pages
│   │   └── components/
│   └── package.json
├── static/
│   └── webllm.html             # WebLLM standalone interface
├── uploads/                    # Temporary uploads (auto-cleaned)
└── outputs/                    # Translated files (auto-cleaned)

🛠️ Tech Stack

Backend

• FastAPI: Modern async web framework
• openpyxl: Excel manipulation
• python-docx: Word documents
• python-pptx: PowerPoint presentations
• deep-translator: Google/DeepL/Libre translation
• psutil: System monitoring
• python-magic: File type validation

Frontend

• Next.js 15: React framework
• Tailwind CSS: Styling
• Lucide Icons: Icon library
• WebLLM: Browser-based LLM

🔌 MCP Integration

This API can be used as an MCP (Model Context Protocol) server for AI assistants.

VS Code Configuration

Add to your VS Code settings.json or .vscode/mcp.json:

{
  "servers": {
    "document-translator": {
      "type": "stdio",
      "command": "python",
      "args": ["mcp_server.py"],
      "cwd": "D:/Translate",
      "env": {
        "PYTHONPATH": "D:/Translate"
      }
    }
  }
}

🚀 Production Deployment

Security Checklist

• Change ADMIN_PASSWORD or set ADMIN_PASSWORD_HASH
• Set CORS_ORIGINS to your frontend domain
• Enable ENABLE_HSTS=true if using HTTPS
• Configure rate limits appropriately
• Set up log rotation for logs/ directory
• Use a reverse proxy (nginx/traefik) for HTTPS

Docker Deployment (Coming Soon)

FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 8000
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

📝 License

MIT License

🤝 Contributing

Contributions welcome! Please submit a Pull Request.

---

Built with ❤️ using Python, FastAPI, Next.js, and Ollama