| Name | gpt-po-translator JSON |
| Version |
1.3.0
JSON |
| download |
| home_page | None |
| Summary | A CLI tool for translating .po files using GPT models. |
| upload_time | 2025-10-08 14:40:36 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# GPT-PO Translator
[](https://github.com/pescheckit/python-gpt-po/actions/workflows/ci-cd.yml)
**Translate gettext (.po) files using AI models.** Supports OpenAI, Azure OpenAI, Anthropic/Claude, DeepSeek, and Ollama (local) with automatic AI translation tagging.
## 🚀 Quick Start
```bash
# Install
pip install gpt-po-translator
# Set API key
export OPENAI_API_KEY='your_api_key_here'
# Auto-detect and translate all languages
gpt-po-translator --folder ./locales --bulk
```
## ✨ Key Features
- **Multiple AI providers** - OpenAI, Azure OpenAI, Anthropic/Claude, DeepSeek, and Ollama (local)
- **Privacy option** - Use Ollama for local, offline translations with no cloud API
- **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)
```bash
pip install gpt-po-translator
```
### Docker
```bash
docker pull ghcr.io/pescheckit/python-gpt-po:latest
```
### Manual
```bash
git clone https://github.com/pescheckit/python-gpt-po.git
cd python-gpt-po
pip install -e .
```
## 🔧 Setup
### API Keys (Cloud Providers)
Choose your AI provider and set the corresponding API key:
```bash
# 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'
```
### Or Use Ollama (Local, No API Key Needed)
```bash
# 1. Install Ollama
curl -fsSL https://ollama.com/install.sh | sh
# 2. Pull a model
ollama pull qwen2.5 # Best for multilingual (Arabic, Chinese, etc.)
# OR
ollama pull llama3.2 # Fast for European languages
# 3. Translate (no API key required!)
gpt-po-translator --provider ollama --folder ./locales
# For non-Latin scripts, use qwen2.5 WITHOUT --bulk
gpt-po-translator --provider ollama --model qwen2.5 --folder ./locales --lang ar
```
> **💡 Important:** For Ollama with **non-Latin languages** (Arabic, Chinese, Japanese, etc.), **omit the `--bulk` flag**. Single-item translation is more reliable because the model doesn't have to format responses as JSON.
## 💡 Usage Examples
### Basic Translation
```bash
# Auto-detect languages from PO files (recommended)
gpt-po-translator --folder ./locales --bulk -v
# Or specify languages explicitly
gpt-po-translator --folder ./locales --lang de,fr,es --bulk -v
# Single language with progress information
gpt-po-translator --folder ./locales --lang de -v
```
### Different AI Providers
```bash
# Use Claude (Anthropic) - auto-detect languages
gpt-po-translator --provider anthropic --folder ./locales --bulk
# Use DeepSeek with specific languages
gpt-po-translator --provider deepseek --folder ./locales --lang de
# Use Azure OpenAI with auto-detection
gpt-po-translator --provider azure_openai --folder ./locales --bulk
# Use Ollama (local, private, free) - omit --bulk for non-Latin scripts
gpt-po-translator --provider ollama --folder ./locales
```
### Docker Usage
```bash
# Basic usage with OpenAI
docker run -v $(pwd):/data \
-e OPENAI_API_KEY="your_key" \
ghcr.io/pescheckit/python-gpt-po:latest \
--folder /data --bulk
# With Ollama (local, no API key needed)
# Note: Omit --bulk for better quality with non-Latin scripts
docker run --rm \
-v $(pwd):/data \
--network host \
ghcr.io/pescheckit/python-gpt-po:latest \
--provider ollama \
--folder /data
# 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:
```po
#. 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`, `fr_CA`, `pt_BR`) |
| `--provider` | AI provider: `openai`, `azure_openai`, `anthropic`, `deepseek`, `ollama` |
| `--bulk` | Enable batch translation (recommended for large files) |
| `--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 |
| `--ollama-base-url` | Ollama server URL (default: `http://localhost:11434`) |
| `--ollama-timeout` | Ollama timeout in seconds (default: 120) |
| `-v, --verbose` | Show progress information (use `-vv` for debug) |
| `-q, --quiet` | Only show errors |
| `--version` | Show version and exit |
## 🛠️ Development
### Build Docker Locally
```bash
git clone https://github.com/pescheckit/python-gpt-po.git
cd python-gpt-po
docker build -t python-gpt-po .
```
### Run Tests
```bash
# 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](docs/usage.md)** - Comprehensive options and mechanics
- **[Development Guide](docs/development.md)** - Contributing guidelines
- **[GitHub Issues](https://github.com/pescheckit/python-gpt-po/issues)** - Bug reports and feature requests
## 📄 License
MIT License - See [LICENSE](LICENSE) for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "gpt-po-translator",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Bram Mittendorff <bram@pescheck.io>",
"download_url": "https://files.pythonhosted.org/packages/67/90/d45ed88b938c5abdaeba746e6cae66a4101cca472b098ab5f3cad1b81df4/gpt_po_translator-1.3.0.tar.gz",
"platform": null,
"description": "# GPT-PO Translator\n\n[](https://github.com/pescheckit/python-gpt-po/actions/workflows/ci-cd.yml)\n\n\n\n**Translate gettext (.po) files using AI models.** Supports OpenAI, Azure OpenAI, Anthropic/Claude, DeepSeek, and Ollama (local) with automatic AI translation tagging.\n\n## \ud83d\ude80 Quick Start\n\n```bash\n# Install\npip install gpt-po-translator\n\n# Set API key\nexport OPENAI_API_KEY='your_api_key_here'\n\n# Auto-detect and translate all languages\ngpt-po-translator --folder ./locales --bulk\n```\n\n## \u2728 Key Features\n\n- **Multiple AI providers** - OpenAI, Azure OpenAI, Anthropic/Claude, DeepSeek, and Ollama (local)\n- **Privacy option** - Use Ollama for local, offline translations with no cloud API\n- **AI translation tracking** - Auto-tags AI-generated translations with `#. AI-generated` comments\n- **Bulk processing** - Efficient batch translation for large files\n- **Smart language detection** - Auto-detects target languages from folder structure\n- **Fuzzy entry handling** - Translates and fixes fuzzy entries properly\n- **Docker ready** - Available as container for easy deployment\n\n## \ud83d\udce6 Installation\n\n### PyPI (Recommended)\n```bash\npip install gpt-po-translator\n```\n\n### Docker\n```bash\ndocker pull ghcr.io/pescheckit/python-gpt-po:latest\n```\n\n### Manual\n```bash\ngit clone https://github.com/pescheckit/python-gpt-po.git\ncd python-gpt-po\npip install -e .\n```\n\n## \ud83d\udd27 Setup\n\n### API Keys (Cloud Providers)\n\nChoose your AI provider and set the corresponding API key:\n\n```bash\n# OpenAI\nexport OPENAI_API_KEY='your_key'\n\n# Anthropic/Claude\nexport ANTHROPIC_API_KEY='your_key'\n\n# DeepSeek\nexport DEEPSEEK_API_KEY='your_key'\n\n# Azure OpenAI\nexport AZURE_OPENAI_API_KEY='your_key'\nexport AZURE_OPENAI_ENDPOINT='https://your-resource.openai.azure.com/'\nexport AZURE_OPENAI_API_VERSION='2024-02-01'\n```\n\n### Or Use Ollama (Local, No API Key Needed)\n\n```bash\n# 1. Install Ollama\ncurl -fsSL https://ollama.com/install.sh | sh\n\n# 2. Pull a model\nollama pull qwen2.5 # Best for multilingual (Arabic, Chinese, etc.)\n# OR\nollama pull llama3.2 # Fast for European languages\n\n# 3. Translate (no API key required!)\ngpt-po-translator --provider ollama --folder ./locales\n\n# For non-Latin scripts, use qwen2.5 WITHOUT --bulk\ngpt-po-translator --provider ollama --model qwen2.5 --folder ./locales --lang ar\n```\n\n> **\ud83d\udca1 Important:** For Ollama with **non-Latin languages** (Arabic, Chinese, Japanese, etc.), **omit the `--bulk` flag**. Single-item translation is more reliable because the model doesn't have to format responses as JSON.\n\n## \ud83d\udca1 Usage Examples\n\n### Basic Translation\n```bash\n# Auto-detect languages from PO files (recommended)\ngpt-po-translator --folder ./locales --bulk -v\n\n# Or specify languages explicitly\ngpt-po-translator --folder ./locales --lang de,fr,es --bulk -v\n\n# Single language with progress information\ngpt-po-translator --folder ./locales --lang de -v\n```\n\n### Different AI Providers\n```bash\n# Use Claude (Anthropic) - auto-detect languages\ngpt-po-translator --provider anthropic --folder ./locales --bulk\n\n# Use DeepSeek with specific languages\ngpt-po-translator --provider deepseek --folder ./locales --lang de\n\n# Use Azure OpenAI with auto-detection\ngpt-po-translator --provider azure_openai --folder ./locales --bulk\n\n# Use Ollama (local, private, free) - omit --bulk for non-Latin scripts\ngpt-po-translator --provider ollama --folder ./locales\n```\n\n### Docker Usage\n```bash\n# Basic usage with OpenAI\ndocker run -v $(pwd):/data \\\n -e OPENAI_API_KEY=\"your_key\" \\\n ghcr.io/pescheckit/python-gpt-po:latest \\\n --folder /data --bulk\n\n# With Ollama (local, no API key needed)\n# Note: Omit --bulk for better quality with non-Latin scripts\ndocker run --rm \\\n -v $(pwd):/data \\\n --network host \\\n ghcr.io/pescheckit/python-gpt-po:latest \\\n --provider ollama \\\n --folder /data\n\n# With Azure OpenAI\ndocker run -v $(pwd):/data \\\n -e AZURE_OPENAI_API_KEY=\"your_key\" \\\n -e AZURE_OPENAI_ENDPOINT=\"https://your-resource.openai.azure.com/\" \\\n -e AZURE_OPENAI_API_VERSION=\"2024-02-01\" \\\n ghcr.io/pescheckit/python-gpt-po:latest \\\n --provider azure_openai --folder /data --lang de\n```\n\n## \ud83c\udff7\ufe0f AI Translation Tracking\n\n**All AI translations are automatically tagged** for transparency and compliance:\n\n```po\n#. AI-generated\nmsgid \"Hello\"\nmsgstr \"Hallo\"\n```\n\nThis helps you:\n- Track which translations are AI vs human-generated\n- Comply with AI content disclosure requirements\n- Manage incremental translation workflows\n\n**Note:** Django's `makemessages` removes these comments but preserves translations. Re-run the translator after `makemessages` to restore tags.\n\n## \ud83d\udcda Command Reference\n\n| Option | Description |\n|--------|-------------|\n| `--folder` | Path to .po files |\n| `--lang` | Target languages (e.g., `de,fr,es`, `fr_CA`, `pt_BR`) |\n| `--provider` | AI provider: `openai`, `azure_openai`, `anthropic`, `deepseek`, `ollama` |\n| `--bulk` | Enable batch translation (recommended for large files) |\n| `--bulksize` | Entries per batch (default: 50) |\n| `--model` | Specific model to use |\n| `--list-models` | Show available models |\n| `--fix-fuzzy` | Translate fuzzy entries |\n| `--folder-language` | Auto-detect languages from folders |\n| `--no-ai-comment` | Disable AI tagging |\n| `--ollama-base-url` | Ollama server URL (default: `http://localhost:11434`) |\n| `--ollama-timeout` | Ollama timeout in seconds (default: 120) |\n| `-v, --verbose` | Show progress information (use `-vv` for debug) |\n| `-q, --quiet` | Only show errors |\n| `--version` | Show version and exit |\n\n## \ud83d\udee0\ufe0f Development\n\n### Build Docker Locally\n```bash\ngit clone https://github.com/pescheckit/python-gpt-po.git\ncd python-gpt-po\ndocker build -t python-gpt-po .\n```\n\n### Run Tests\n```bash\n# Local\npython -m pytest\n\n# Docker\ndocker run --rm -v $(pwd):/app -w /app --entrypoint python python-gpt-po -m pytest -v\n```\n\n## \ud83d\udccb Requirements\n\n- Python 3.9+\n- Dependencies: `polib`, `openai`, `anthropic`, `requests`, `tenacity`\n\n## \ud83d\udcd6 Documentation\n\n- **[Advanced Usage Guide](docs/usage.md)** - Comprehensive options and mechanics\n- **[Development Guide](docs/development.md)** - Contributing guidelines\n- **[GitHub Issues](https://github.com/pescheckit/python-gpt-po/issues)** - Bug reports and feature requests\n\n## \ud83d\udcc4 License\n\nMIT License - See [LICENSE](LICENSE) for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A CLI tool for translating .po files using GPT models.",
"version": "1.3.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "9b2d47917f5310a088b973c5f47aed5ea2cd93f6ef21dad2a688217e249a80a8",
"md5": "6f98410753a74c8c7dd513fcc2e4b7d4",
"sha256": "72b7e45ac6fd66e4f9a8c50c4d3df94deb617debc41dedb81057ded7778e9d71"
},
"downloads": -1,
"filename": "gpt_po_translator-1.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6f98410753a74c8c7dd513fcc2e4b7d4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 110868,
"upload_time": "2025-10-08T14:40:35",
"upload_time_iso_8601": "2025-10-08T14:40:35.648159Z",
"url": "https://files.pythonhosted.org/packages/9b/2d/47917f5310a088b973c5f47aed5ea2cd93f6ef21dad2a688217e249a80a8/gpt_po_translator-1.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6790d45ed88b938c5abdaeba746e6cae66a4101cca472b098ab5f3cad1b81df4",
"md5": "eb958e5c7379635a003c00cd2c07e8f7",
"sha256": "55a5535148dab0105d95379350e18aaed66ca7d180004f0ab4c421c165b35e82"
},
"downloads": -1,
"filename": "gpt_po_translator-1.3.0.tar.gz",
"has_sig": false,
"md5_digest": "eb958e5c7379635a003c00cd2c07e8f7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 95177,
"upload_time": "2025-10-08T14:40:36",
"upload_time_iso_8601": "2025-10-08T14:40:36.693666Z",
"url": "https://files.pythonhosted.org/packages/67/90/d45ed88b938c5abdaeba746e6cae66a4101cca472b098ab5f3cad1b81df4/gpt_po_translator-1.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-08 14:40:36",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "gpt-po-translator"
}
