# 🚀 RAG Studio
**Production-ready document processing CLI for RAG applications**
Process documents, extract text with advanced OCR, chunk intelligently, and prepare data for RAG systems - all from the command line with `ragctl`.
[](https://github.com/horiz-data/ragstudio)
[](https://pypi.org/project/ragctl/)
[](https://github.com/horiz-data/ragstudio)
[](https://github.com/horiz-data/ragstudio)
[](https://github.com/horiz-data/ragstudio)
[](LICENSE)
[](https://www.python.org/downloads/)
---
## 🎯 What is RAG Studio?
RAG Studio (`ragctl`) is a **command-line tool** for processing documents into chunks ready for Retrieval-Augmented Generation (RAG) systems. It handles the dirty work of document ingestion, OCR, and intelligent chunking so you can focus on building your RAG application.
**Key capabilities:**
- 📄 Universal document loading (PDF, DOCX, images, HTML, Markdown, etc.)
- 🔍 Advanced OCR with automatic fallback (EasyOCR → PaddleOCR → pytesseract)
- ✂️ Intelligent semantic chunking using LangChain
- 📦 Production-ready batch processing with auto-retry
- 💾 Multiple export formats (JSON, JSONL, CSV)
- 🗄️ Direct ingestion into Qdrant vector store
---
## ✨ Features
### 📄 Universal Document Processing
- **Supported formats**: PDF, DOCX, ODT, TXT, HTML, Markdown, Images (JPEG, PNG)
- **Smart OCR cascade**:
1. EasyOCR (best quality, multi-language)
2. PaddleOCR (fast, good for complex layouts)
3. pytesseract (fallback, most tolerant)
- **Quality detection**: Automatically rejects unreadable documents
- **Multi-language**: French, English, German, Spanish, Italian, Portuguese, and more
### ✂️ Intelligent Chunking
- **Semantic chunking**: Context-aware text splitting using LangChain RecursiveCharacterTextSplitter
- **Multiple strategies**:
- `semantic` - Smart splitting by meaning (default)
- `sentence` - Split by sentences
- `token` - Fixed token-based splitting
- **Configurable**: Token limits (50-2000), overlap (0-500), model selection
- **Rich metadata**: Source file, chunk index, token count, strategy, timestamps
### 🔄 Production-Ready Batch Processing
- **Automatic retry**: Up to 3 attempts with exponential backoff (1s, 2s, 4s...)
- **Interactive error handling**:
- `interactive` - Prompt user on each error (default)
- `auto-continue` - Continue on errors (CI/CD mode)
- `auto-stop` - Stop on first error (validation mode)
- `auto-skip` - Skip failed files automatically
- **Complete history**: Every run saved to `~/.atlasrag/history/`
- **Retry capability**: `ragctl retry` to rerun failed files only
- **Per-file output**: One chunk file per document for better traceability
### 💾 Flexible Export & Storage
- **Export formats**: JSON, JSONL (streaming), CSV (Excel-compatible)
- **Vector store integration**: Direct ingestion into Qdrant
- **No database required**: Pure file-based export for easy sharing
### ⚙️ Configuration System
- **Hierarchical config**: CLI flags > Environment variables > YAML file > Defaults
- **Example config**: `config.example.yml` with detailed documentation
- **Easy customization**: Override any setting via command line
---
## 🚀 Quick Start
### Installation
#### From PyPI (Recommended)
```bash
# Install from PyPI
pip install ragctl
# Verify installation
ragctl --version
```
#### From Source
```bash
# Clone repository
git clone git@github.com:horiz-data/ragstudio.git
cd ragstudio
# Install with pip
pip install -e .
# Verify installation
ragctl --version
```
### Basic Usage
```bash
# Process a single document
ragctl chunk document.pdf --show
# Process with advanced OCR for scanned documents
ragctl chunk scanned.pdf --advanced-ocr -o chunks.json
# Batch process a folder
ragctl batch ./documents --output ./chunks/
# Batch with auto-retry for CI/CD
ragctl batch ./documents --output ./chunks/ --auto-continue
```
---
## 💡 Usage Examples
### Single Document Processing
```bash
# Simple text file
ragctl chunk document.txt --show
# PDF with semantic chunking (default)
ragctl chunk report.pdf -o report_chunks.json
# Scanned image with OCR
ragctl chunk contract.jpeg --advanced-ocr --show
# Custom chunking parameters
ragctl chunk document.pdf \
--strategy semantic \
--max-tokens 500 \
--overlap 100 \
-o output.jsonl
```
### Batch Processing
```bash
# Process all files in a directory
ragctl batch ./documents --output ./chunks/
# Process only PDFs recursively
ragctl batch ./documents \
--pattern "*.pdf" \
--recursive \
--output ./chunks/
# CI/CD mode - continue on errors
ragctl batch ./documents \
--output ./chunks/ \
--auto-continue \
--save-history
# Per-file output (default):
# chunks/
# ├── doc1_chunks.jsonl (25 chunks)
# ├── doc2_chunks.jsonl (42 chunks)
# └── doc3_chunks.jsonl (18 chunks)
# Single-file output (all chunks combined):
ragctl batch ./documents \
--output ./all_chunks.jsonl \
--single-file
```
### Retry Failed Files
```bash
# Show last failed run
ragctl retry --show
# Retry all failed files from last run
ragctl retry
# Retry specific run by ID
ragctl retry run_20251028_133403
```
### Vector Store Integration
```bash
# Ingest chunks into Qdrant
ragctl ingest chunks.jsonl \
--collection my-docs \
--url http://localhost:6333
# Get system info
ragctl info
```
### Evaluate Chunking Quality
```bash
# Evaluate chunking strategy
ragctl eval document.pdf \
--strategies semantic sentence token \
--metrics coverage overlap coherence
# Compare strategies with visualization
ragctl eval document.pdf --compare --output eval_results.json
```
---
## 📚 Documentation
| Document | Description |
|----------|-------------|
| **[Getting Started](docs/getting-started.md)** | Installation and first steps |
| **[CLI Guide](docs/cli-guide.md)** | Complete command reference |
| **[Security](docs/security/)** | Security features and best practices |
| **[Full Documentation](docs/)** | Complete documentation index |
---
## ⚙️ Configuration
Create `~/.atlasrag/config.yml` or use CLI flags:
```yaml
# OCR settings
ocr:
use_advanced_ocr: false
enable_fallback: true
# Chunking settings
chunking:
strategy: semantic
max_tokens: 400
overlap: 50
# Output settings
output:
format: jsonl
include_metadata: true
pretty_print: true
```
**Configuration hierarchy**: CLI flags > Environment variables > YAML config > Defaults
---
## 🧪 Testing
```bash
# Run all tests
make test
# Run CLI tests
make test-cli
# Quick validation
ragctl --version
ragctl chunk tests/data/sample.txt --show
```
**Test Coverage**: 129 tests, 96% coverage
---
## 📊 Performance
### Processing Speed
- **Text documents**: ~100-200 docs/minute
- **PDFs with OCR**: ~5-10 docs/minute (depends on page count)
- **Batch processing**: Parallel-ready with retry mechanism
### Quality Metrics
- **OCR accuracy**: 95%+ with EasyOCR on clear scans
- **Chunk quality**: 90% readability threshold enforced
- **Semantic coherence**: LangChain's RecursiveCharacterTextSplitter optimized for context
---
## 🛠️ CLI Commands
| Command | Description |
|---------|-------------|
| `ragctl chunk` | Process a single document |
| `ragctl batch` | Batch process multiple files |
| `ragctl retry` | Retry failed files from history |
| `ragctl ingest` | Ingest chunks into Qdrant |
| `ragctl eval` | Evaluate chunking quality |
| `ragctl info` | System information |
Run `ragctl COMMAND --help` for detailed options.
---
## 🐛 Troubleshooting
### Common Issues
**NumPy incompatibility**
```bash
# For OCR support, use NumPy 1.x
pip install "numpy<2.0"
```
**Missing system dependencies**
```bash
# Ubuntu/Debian
sudo apt-get install tesseract-ocr poppler-utils
# macOS
brew install tesseract poppler
```
**"Document unreadable" errors**
- Try lowering quality threshold: `--ocr-threshold 0.2`
- Use advanced OCR: `--advanced-ocr`
- Check document is not corrupted
**Import errors**
```bash
# Reinstall dependencies
pip install -e .
```
More help: [Getting Started Guide](docs/getting-started.md#troubleshooting)
---
## 🔧 Development
```bash
# Install dev dependencies
make install-dev
# Format code
make format
# Run linters
make lint
# Install pre-commit hooks
make pre-commit-install
# Run all CI checks
make ci-all
```
---
## 📝 License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
---
## 🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines (coming soon).
---
## 📧 Support
- **Documentation**: [docs/](docs/)
- **Issues**: [GitHub Issues](https://github.com/horiz-data/ragstudio/issues)
- **Discussions**: [GitHub Discussions](https://github.com/horiz-data/ragstudio/discussions)
---
## 🙏 Acknowledgments
Built with:
- [LangChain](https://github.com/langchain-ai/langchain) - Text splitting and document loading
- [EasyOCR](https://github.com/JaidedAI/EasyOCR) - OCR engine
- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) - Alternative OCR engine
- [Unstructured](https://github.com/Unstructured-IO/unstructured) - Document parsing
- [Typer](https://github.com/tiangolo/typer) - CLI framework
- [Rich](https://github.com/Textualize/rich) - Terminal formatting
---
**Version**: 0.1.2 | **Status**: Beta | **License**: MIT
# Test
Raw data
{
"_id": null,
"home_page": null,
"name": "ragctl",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.10",
"maintainer_email": "Horiz Data <sekkaahmed@gmail.com>",
"keywords": "rag, document-processing, ocr, chunking, nlp, machine-learning, embeddings, semantic-search",
"author": null,
"author_email": "Horiz Data <sekkaahmed@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/70/6b/daa081d1d0cd34ffba0b8c7efa72a6160797480022f7cd54c2c81f517a29/ragctl-0.1.3.tar.gz",
"platform": null,
"description": "# \ud83d\ude80 RAG Studio\n\n**Production-ready document processing CLI for RAG applications**\n\nProcess documents, extract text with advanced OCR, chunk intelligently, and prepare data for RAG systems - all from the command line with `ragctl`.\n\n[](https://github.com/horiz-data/ragstudio)\n[](https://pypi.org/project/ragctl/)\n[](https://github.com/horiz-data/ragstudio)\n[](https://github.com/horiz-data/ragstudio)\n[](https://github.com/horiz-data/ragstudio)\n[](LICENSE)\n[](https://www.python.org/downloads/)\n\n---\n\n## \ud83c\udfaf What is RAG Studio?\n\nRAG Studio (`ragctl`) is a **command-line tool** for processing documents into chunks ready for Retrieval-Augmented Generation (RAG) systems. It handles the dirty work of document ingestion, OCR, and intelligent chunking so you can focus on building your RAG application.\n\n**Key capabilities:**\n- \ud83d\udcc4 Universal document loading (PDF, DOCX, images, HTML, Markdown, etc.)\n- \ud83d\udd0d Advanced OCR with automatic fallback (EasyOCR \u2192 PaddleOCR \u2192 pytesseract)\n- \u2702\ufe0f Intelligent semantic chunking using LangChain\n- \ud83d\udce6 Production-ready batch processing with auto-retry\n- \ud83d\udcbe Multiple export formats (JSON, JSONL, CSV)\n- \ud83d\uddc4\ufe0f Direct ingestion into Qdrant vector store\n\n---\n\n## \u2728 Features\n\n### \ud83d\udcc4 Universal Document Processing\n- **Supported formats**: PDF, DOCX, ODT, TXT, HTML, Markdown, Images (JPEG, PNG)\n- **Smart OCR cascade**:\n 1. EasyOCR (best quality, multi-language)\n 2. PaddleOCR (fast, good for complex layouts)\n 3. pytesseract (fallback, most tolerant)\n- **Quality detection**: Automatically rejects unreadable documents\n- **Multi-language**: French, English, German, Spanish, Italian, Portuguese, and more\n\n### \u2702\ufe0f Intelligent Chunking\n- **Semantic chunking**: Context-aware text splitting using LangChain RecursiveCharacterTextSplitter\n- **Multiple strategies**:\n - `semantic` - Smart splitting by meaning (default)\n - `sentence` - Split by sentences\n - `token` - Fixed token-based splitting\n- **Configurable**: Token limits (50-2000), overlap (0-500), model selection\n- **Rich metadata**: Source file, chunk index, token count, strategy, timestamps\n\n### \ud83d\udd04 Production-Ready Batch Processing\n- **Automatic retry**: Up to 3 attempts with exponential backoff (1s, 2s, 4s...)\n- **Interactive error handling**:\n - `interactive` - Prompt user on each error (default)\n - `auto-continue` - Continue on errors (CI/CD mode)\n - `auto-stop` - Stop on first error (validation mode)\n - `auto-skip` - Skip failed files automatically\n- **Complete history**: Every run saved to `~/.atlasrag/history/`\n- **Retry capability**: `ragctl retry` to rerun failed files only\n- **Per-file output**: One chunk file per document for better traceability\n\n### \ud83d\udcbe Flexible Export & Storage\n- **Export formats**: JSON, JSONL (streaming), CSV (Excel-compatible)\n- **Vector store integration**: Direct ingestion into Qdrant\n- **No database required**: Pure file-based export for easy sharing\n\n### \u2699\ufe0f Configuration System\n- **Hierarchical config**: CLI flags > Environment variables > YAML file > Defaults\n- **Example config**: `config.example.yml` with detailed documentation\n- **Easy customization**: Override any setting via command line\n\n---\n\n## \ud83d\ude80 Quick Start\n\n### Installation\n\n#### From PyPI (Recommended)\n\n```bash\n# Install from PyPI\npip install ragctl\n\n# Verify installation\nragctl --version\n```\n\n#### From Source\n\n```bash\n# Clone repository\ngit clone git@github.com:horiz-data/ragstudio.git\ncd ragstudio\n\n# Install with pip\npip install -e .\n\n# Verify installation\nragctl --version\n```\n\n### Basic Usage\n\n```bash\n# Process a single document\nragctl chunk document.pdf --show\n\n# Process with advanced OCR for scanned documents\nragctl chunk scanned.pdf --advanced-ocr -o chunks.json\n\n# Batch process a folder\nragctl batch ./documents --output ./chunks/\n\n# Batch with auto-retry for CI/CD\nragctl batch ./documents --output ./chunks/ --auto-continue\n```\n\n---\n\n## \ud83d\udca1 Usage Examples\n\n### Single Document Processing\n\n```bash\n# Simple text file\nragctl chunk document.txt --show\n\n# PDF with semantic chunking (default)\nragctl chunk report.pdf -o report_chunks.json\n\n# Scanned image with OCR\nragctl chunk contract.jpeg --advanced-ocr --show\n\n# Custom chunking parameters\nragctl chunk document.pdf \\\n --strategy semantic \\\n --max-tokens 500 \\\n --overlap 100 \\\n -o output.jsonl\n```\n\n### Batch Processing\n\n```bash\n# Process all files in a directory\nragctl batch ./documents --output ./chunks/\n\n# Process only PDFs recursively\nragctl batch ./documents \\\n --pattern \"*.pdf\" \\\n --recursive \\\n --output ./chunks/\n\n# CI/CD mode - continue on errors\nragctl batch ./documents \\\n --output ./chunks/ \\\n --auto-continue \\\n --save-history\n\n# Per-file output (default):\n# chunks/\n# \u251c\u2500\u2500 doc1_chunks.jsonl (25 chunks)\n# \u251c\u2500\u2500 doc2_chunks.jsonl (42 chunks)\n# \u2514\u2500\u2500 doc3_chunks.jsonl (18 chunks)\n\n# Single-file output (all chunks combined):\nragctl batch ./documents \\\n --output ./all_chunks.jsonl \\\n --single-file\n```\n\n### Retry Failed Files\n\n```bash\n# Show last failed run\nragctl retry --show\n\n# Retry all failed files from last run\nragctl retry\n\n# Retry specific run by ID\nragctl retry run_20251028_133403\n```\n\n### Vector Store Integration\n\n```bash\n# Ingest chunks into Qdrant\nragctl ingest chunks.jsonl \\\n --collection my-docs \\\n --url http://localhost:6333\n\n# Get system info\nragctl info\n```\n\n### Evaluate Chunking Quality\n\n```bash\n# Evaluate chunking strategy\nragctl eval document.pdf \\\n --strategies semantic sentence token \\\n --metrics coverage overlap coherence\n\n# Compare strategies with visualization\nragctl eval document.pdf --compare --output eval_results.json\n```\n\n---\n\n## \ud83d\udcda Documentation\n\n| Document | Description |\n|----------|-------------|\n| **[Getting Started](docs/getting-started.md)** | Installation and first steps |\n| **[CLI Guide](docs/cli-guide.md)** | Complete command reference |\n| **[Security](docs/security/)** | Security features and best practices |\n| **[Full Documentation](docs/)** | Complete documentation index |\n\n---\n\n## \u2699\ufe0f Configuration\n\nCreate `~/.atlasrag/config.yml` or use CLI flags:\n\n```yaml\n# OCR settings\nocr:\n use_advanced_ocr: false\n enable_fallback: true\n\n# Chunking settings\nchunking:\n strategy: semantic\n max_tokens: 400\n overlap: 50\n\n# Output settings\noutput:\n format: jsonl\n include_metadata: true\n pretty_print: true\n```\n\n**Configuration hierarchy**: CLI flags > Environment variables > YAML config > Defaults\n\n---\n\n## \ud83e\uddea Testing\n\n```bash\n# Run all tests\nmake test\n\n# Run CLI tests\nmake test-cli\n\n# Quick validation\nragctl --version\nragctl chunk tests/data/sample.txt --show\n```\n\n**Test Coverage**: 129 tests, 96% coverage\n\n---\n\n## \ud83d\udcca Performance\n\n### Processing Speed\n- **Text documents**: ~100-200 docs/minute\n- **PDFs with OCR**: ~5-10 docs/minute (depends on page count)\n- **Batch processing**: Parallel-ready with retry mechanism\n\n### Quality Metrics\n- **OCR accuracy**: 95%+ with EasyOCR on clear scans\n- **Chunk quality**: 90% readability threshold enforced\n- **Semantic coherence**: LangChain's RecursiveCharacterTextSplitter optimized for context\n\n---\n\n## \ud83d\udee0\ufe0f CLI Commands\n\n| Command | Description |\n|---------|-------------|\n| `ragctl chunk` | Process a single document |\n| `ragctl batch` | Batch process multiple files |\n| `ragctl retry` | Retry failed files from history |\n| `ragctl ingest` | Ingest chunks into Qdrant |\n| `ragctl eval` | Evaluate chunking quality |\n| `ragctl info` | System information |\n\nRun `ragctl COMMAND --help` for detailed options.\n\n---\n\n## \ud83d\udc1b Troubleshooting\n\n### Common Issues\n\n**NumPy incompatibility**\n```bash\n# For OCR support, use NumPy 1.x\npip install \"numpy<2.0\"\n```\n\n**Missing system dependencies**\n```bash\n# Ubuntu/Debian\nsudo apt-get install tesseract-ocr poppler-utils\n\n# macOS\nbrew install tesseract poppler\n```\n\n**\"Document unreadable\" errors**\n- Try lowering quality threshold: `--ocr-threshold 0.2`\n- Use advanced OCR: `--advanced-ocr`\n- Check document is not corrupted\n\n**Import errors**\n```bash\n# Reinstall dependencies\npip install -e .\n```\n\nMore help: [Getting Started Guide](docs/getting-started.md#troubleshooting)\n\n---\n\n## \ud83d\udd27 Development\n\n```bash\n# Install dev dependencies\nmake install-dev\n\n# Format code\nmake format\n\n# Run linters\nmake lint\n\n# Install pre-commit hooks\nmake pre-commit-install\n\n# Run all CI checks\nmake ci-all\n```\n\n---\n\n## \ud83d\udcdd License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n\n## \ud83e\udd1d Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines (coming soon).\n\n---\n\n## \ud83d\udce7 Support\n\n- **Documentation**: [docs/](docs/)\n- **Issues**: [GitHub Issues](https://github.com/horiz-data/ragstudio/issues)\n- **Discussions**: [GitHub Discussions](https://github.com/horiz-data/ragstudio/discussions)\n\n---\n\n## \ud83d\ude4f Acknowledgments\n\nBuilt with:\n- [LangChain](https://github.com/langchain-ai/langchain) - Text splitting and document loading\n- [EasyOCR](https://github.com/JaidedAI/EasyOCR) - OCR engine\n- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) - Alternative OCR engine\n- [Unstructured](https://github.com/Unstructured-IO/unstructured) - Document parsing\n- [Typer](https://github.com/tiangolo/typer) - CLI framework\n- [Rich](https://github.com/Textualize/rich) - Terminal formatting\n\n---\n\n**Version**: 0.1.2 | **Status**: Beta | **License**: MIT\n# Test\n",
"bugtrack_url": null,
"license": null,
"summary": "RAG Studio - Production-ready RAG toolkit with advanced OCR, semantic chunking, and intelligent document processing",
"version": "0.1.3",
"project_urls": {
"Changelog": "https://github.com/horiz-data/ragstudio/blob/main/CHANGELOG.md",
"Documentation": "https://github.com/horiz-data/ragstudio/tree/main/docs",
"Homepage": "https://github.com/horiz-data/ragstudio",
"Issues": "https://github.com/horiz-data/ragstudio/issues",
"Repository": "https://github.com/horiz-data/ragstudio"
},
"split_keywords": [
"rag",
" document-processing",
" ocr",
" chunking",
" nlp",
" machine-learning",
" embeddings",
" semantic-search"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "8aa1db784d275041a8be04430611304dc8e44c60b9db839f4d8120ea5ac7e5a2",
"md5": "80fe24de313aa100dc976e30fd3a8a3f",
"sha256": "679a676bba612c92233655c7136ee2e3108fb77f97d540b7e2599847f89086f7"
},
"downloads": -1,
"filename": "ragctl-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "80fe24de313aa100dc976e30fd3a8a3f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.10",
"size": 238051,
"upload_time": "2025-10-30T10:41:18",
"upload_time_iso_8601": "2025-10-30T10:41:18.659397Z",
"url": "https://files.pythonhosted.org/packages/8a/a1/db784d275041a8be04430611304dc8e44c60b9db839f4d8120ea5ac7e5a2/ragctl-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "706bdaa081d1d0cd34ffba0b8c7efa72a6160797480022f7cd54c2c81f517a29",
"md5": "ac00cf7376ecc735e6e36f55789ea15c",
"sha256": "66fa9f87ca5236037c37576360bfd710915fa721ae4fd88101bc7b3393048a0a"
},
"downloads": -1,
"filename": "ragctl-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "ac00cf7376ecc735e6e36f55789ea15c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.10",
"size": 192770,
"upload_time": "2025-10-30T10:41:20",
"upload_time_iso_8601": "2025-10-30T10:41:20.429716Z",
"url": "https://files.pythonhosted.org/packages/70/6b/daa081d1d0cd34ffba0b8c7efa72a6160797480022f7cd54c2c81f517a29/ragctl-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-30 10:41:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "horiz-data",
"github_project": "ragstudio",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "ragctl"
}
JSON
