GPT-PO Translator

Translate gettext (.po) files using AI models. Supports OpenAI, Azure OpenAI, Anthropic/Claude, and DeepSeek with automatic AI translation tagging.

🚀 Quick Start

# Install
pip install gpt-po-translator

# Set API key
export OPENAI_API_KEY='your_api_key_here'

# Translate to German and French
gpt-po-translator --folder ./locales --lang de,fr --bulk

✨ Key Features

• Multiple AI providers - OpenAI, Azure OpenAI, Anthropic/Claude, DeepSeek
• AI translation tracking - Auto-tags AI-generated translations with #. AI-generated comments
• Bulk processing - Efficient batch translation for large files
• Smart language detection - Auto-detects target languages from folder structure
• Fuzzy entry handling - Translates and fixes fuzzy entries properly
• Docker ready - Available as container for easy deployment

📦 Installation

PyPI (Recommended)

pip install gpt-po-translator

Docker

docker pull ghcr.io/pescheckit/python-gpt-po:latest

Manual

git clone https://github.com/pescheckit/python-gpt-po.git
cd python-gpt-po
pip install -e .

🔧 Setup

API Keys

Choose your AI provider and set the corresponding API key:

# OpenAI
export OPENAI_API_KEY='your_key'

# Anthropic/Claude
export ANTHROPIC_API_KEY='your_key'

# DeepSeek
export DEEPSEEK_API_KEY='your_key'

# Azure OpenAI
export AZURE_OPENAI_API_KEY='your_key'
export AZURE_OPENAI_ENDPOINT='https://your-resource.openai.azure.com/'
export AZURE_OPENAI_API_VERSION='2024-02-01'

💡 Usage Examples

Basic Translation

# Translate to German
gpt-po-translator --folder ./locales --lang de

# Multiple languages
gpt-po-translator --folder ./locales --lang de,fr,es --bulk

Different AI Providers

# Use Claude (Anthropic)
gpt-po-translator --provider anthropic --folder ./locales --lang de

# Use DeepSeek
gpt-po-translator --provider deepseek --folder ./locales --lang de

# Use Azure OpenAI
gpt-po-translator --provider azure_openai --folder ./locales --lang de

Docker Usage

# Basic usage
docker run -v $(pwd):/data \
  -e OPENAI_API_KEY="your_key" \
  ghcr.io/pescheckit/python-gpt-po:latest \
  --folder /data --lang de,fr --bulk

# With Azure OpenAI
docker run -v $(pwd):/data \
  -e AZURE_OPENAI_API_KEY="your_key" \
  -e AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" \
  -e AZURE_OPENAI_API_VERSION="2024-02-01" \
  ghcr.io/pescheckit/python-gpt-po:latest \
  --provider azure_openai --folder /data --lang de

🏷️ AI Translation Tracking

All AI translations are automatically tagged for transparency and compliance:

#. AI-generated
msgid "Hello"
msgstr "Hallo"

This helps you:

• Track which translations are AI vs human-generated
• Comply with AI content disclosure requirements
• Manage incremental translation workflows

Note: Django's makemessages removes these comments but preserves translations. Re-run the translator after makemessages to restore tags.

📚 Command Reference

Option	Description
--folder	Path to .po files
--lang	Target languages (e.g., de,fr,es)
--provider	AI provider: openai, azure_openai, anthropic, deepseek
--bulk	Enable batch translation (recommended)
--bulksize	Entries per batch (default: 50)
--model	Specific model to use
--list-models	Show available models
--fix-fuzzy	Translate fuzzy entries
--folder-language	Auto-detect languages from folders
--no-ai-comment	Disable AI tagging

🛠️ Development

Build Docker Locally

git clone https://github.com/pescheckit/python-gpt-po.git
cd python-gpt-po
docker build -t python-gpt-po .

Run Tests

# Local
python -m pytest

# Docker
docker run --rm -v $(pwd):/app -w /app --entrypoint python python-gpt-po -m pytest -v

📋 Requirements

• Python 3.9+
• Dependencies: polib, openai, anthropic, requests, tenacity

📖 Documentation

• Advanced Usage Guide - Comprehensive options and mechanics
• Development Guide - Contributing guidelines
• GitHub Issues - Bug reports and feature requests

📄 License

MIT License - See LICENSE for details.