# MARKDROP
<a href="https://pepy.tech/projects/markdrop"><img src="https://static.pepy.tech/badge/markdrop" alt="markdrop total downloads"></a>
A Python package for converting PDFs (or PDF URLs) to markdown while extracting images and tables, with advanced features for AI-powered content analysis and descriptions.
## Features
- [x] PDF to Markdown conversion with formatting preservation using Docling
- [x] Automatic image extraction with quality preservation using XRef Id
- [x] Table detection using Microsoft's Table Transformer
- [x] PDF URL support for core functionalities
- [x] AI-powered image and table descriptions using multiple LLM providers
- [x] Interactive HTML output with downloadable Excel tables
- [x] Customizable image resolution and UI elements
- [x] Comprehensive logging system
- [ ] Optical Character Recognition (OCR) for images with embedded text
- [ ] Support for multi-language PDFs
## Installation
```bash
pip install markdrop
```
> https://pypi.org/project/markdrop
## Quick Start
### Basic PDF Processing
```python
from markdrop import extract_images, make_markdown, extract_tables_from_pdf
source_pdf = 'url/or/path/to/pdf/file' # Replace with your local PDF file path or a URL
output_dir = 'data/output' # Replace with desired output directory's path
make_markdown(source_pdf, output_dir)
extract_images(source_pdf, output_dir)
extract_tables_from_pdf(source_pdf, output_dir=output_dir)
```
### Advanced PDF Processing with MarkDrop
```python
from markdrop import markdrop, MarkDropConfig, add_downloadable_tables
from pathlib import Path
import logging
# Configure processing options
config = MarkDropConfig(
image_resolution_scale=2.0, # Scale factor for image resolution
download_button_color='#444444', # Color for download buttons in HTML
log_level=logging.INFO, # Logging detail level
log_dir='logs', # Directory for log files
excel_dir='markdropped-excel-tables' # Directory for Excel table exports
)
# Process PDF document
input_doc_path = "path/to/input.pdf"
output_dir = Path('output_directory')
# Convert PDF and generate HTML with images and tables
html_path = markdrop(input_doc_path, output_dir, config)
# Add interactive table download functionality
downloadable_html = add_downloadable_tables(html_path, config)
```
### AI-Powered Content Analysis
```python
from markdrop import setup_keys, process_markdown, ProcessorConfig, AIProvider
from pathlib import Path
# Set up API keys for AI providers
setup_keys(key='gemini') # or setup_keys(key='openai')
# Configure AI processing options
config = ProcessorConfig(
input_path="path/to/markdown/file.md", # Input markdown file path
output_dir=Path("output_directory"), # Output directory
ai_provider=AIProvider.GEMINI, # AI provider (GEMINI or OPENAI)
remove_images=False, # Keep or remove original images
remove_tables=False, # Keep or remove original tables
table_descriptions=True, # Generate table descriptions
image_descriptions=True, # Generate image descriptions
max_retries=3, # Number of API call retries
retry_delay=2, # Delay between retries in seconds
gemini_model_name="gemini-1.5-flash", # Gemini model for images
gemini_text_model_name="gemini-pro", # Gemini model for text
image_prompt=DEFAULT_IMAGE_PROMPT, # Custom prompt for image analysis
table_prompt=DEFAULT_TABLE_PROMPT # Custom prompt for table analysis
)
# Process markdown with AI descriptions
output_path = process_markdown(config)
```
### Image Description Generation
```python
from markdrop import generate_descriptions
prompt = "Give textual highly detailed descriptions from this image ONLY, nothing else."
input_path = 'path/to/img_file/or/dir'
output_dir = 'data/output'
llm_clients = ['gemini', 'llama-vision'] # Available: ['qwen', 'gemini', 'openai', 'llama-vision', 'molmo', 'pixtral']
generate_descriptions(
input_path=input_path,
output_dir=output_dir,
prompt=prompt,
llm_client=llm_clients
)
```
## API Reference
### Core Functions
#### markdrop(input_doc_path: str, output_dir: str, config: Optional[MarkDropConfig] = None) -> Path
Converts PDF to markdown and HTML with enhanced features.
Parameters:
- `input_doc_path` (str): Path to input PDF file
- `output_dir` (str): Output directory path
- `config` (MarkDropConfig, optional): Configuration options for processing
#### add_downloadable_tables(html_path: Path, config: Optional[MarkDropConfig] = None) -> Path
Adds interactive table download functionality to HTML output.
Parameters:
- `html_path` (Path): Path to HTML file
- `config` (MarkDropConfig, optional): Configuration options
### Configuration Classes
#### MarkDropConfig
Configuration for PDF processing:
- `image_resolution_scale` (float): Scale factor for image resolution (default: 2.0)
- `download_button_color` (str): HTML color code for download buttons (default: '#444444')
- `log_level` (int): Logging level (default: logging.INFO)
- `log_dir` (str): Directory for log files (default: 'logs')
- `excel_dir` (str): Directory for Excel table exports (default: 'markdropped-excel-tables')
#### ProcessorConfig
Configuration for AI processing:
- `input_path` (str): Path to markdown file
- `output_dir` (str): Output directory path
- `ai_provider` (AIProvider): AI provider selection (GEMINI or OPENAI)
- `remove_images` (bool): Whether to remove original images
- `remove_tables` (bool): Whether to remove original tables
- `table_descriptions` (bool): Generate table descriptions
- `image_descriptions` (bool): Generate image descriptions
- `max_retries` (int): Maximum API call retries
- `retry_delay` (int): Delay between retries in seconds
- `gemini_model_name` (str): Gemini model for image processing
- `gemini_text_model_name` (str): Gemini model for text processing
- `image_prompt` (str): Custom prompt for image analysis
- `table_prompt` (str): Custom prompt for table analysis
### Legacy Functions
#### make_markdown(source: str, output_dir: str, verbose: bool = False)
Legacy function for basic PDF to markdown conversion.
Parameters:
- `source` (str): Path to input PDF or URL
- `output_dir` (str): Output directory path
- `verbose` (bool): Enable detailed logging
#### extract_images(source: str, output_dir: str, verbose: bool = False)
Legacy function for basic image extraction.
Parameters:
- `source` (str): Path to input PDF or URL
- `output_dir` (str): Output directory path
- `verbose` (bool): Enable detailed logging
#### extract_tables_from_pdf(pdf_path: str, **kwargs)
Legacy function for basic table extraction.
Parameters:
- `pdf_path` (str): Path to input PDF or URL
- `start_page` (int, optional): Starting page number
- `end_page` (int, optional): Ending page number
- `threshold` (float, optional): Detection confidence threshold
- `output_dir` (str): Output directory path
## Contributing
We welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details.
### Development Setup
1. Clone the repository:
```bash
git clone https://github.com/shoryasethia/markdrop.git
cd markdrop
```
2. Create a virtual environment:
```bash
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
3. Install development dependencies:
```bash
pip install -r requirements.txt
```
## Project Structure
```bash
markdrop/
├── LICENSE
├── README.md
├── CONTRIBUTING.md
├── CHANGELOG.md
├── requirements.txt
├── setup.py
└── markdrop/
├── __init__.py
├── src
| └── markdrop-logo.png
├── main.py
├── process.py
├── api_setup.py
├── parse.py
├── utils.py
├── helper.py
├── ignore_warnings.py
├── run.py
└── models/
├── __init__.py
├── .env
├── img_descriptions.py
├── logger.py
├── model_loader.py
├── responder.py
└── setup_keys.py
```
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Changelog
See [CHANGELOG.md](CHANGELOG.md) for version history.
## Code of Conduct
Please note that this project follows our [Code of Conduct](CODE_OF_CONDUCT.md).
## Support
- [Open an issue](https://github.com/shoryasethia/markdrop/issues)
Raw data
{
"_id": null,
"home_page": "https://github.com/shoryasethia/markdrop",
"name": "markdrop",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "pdf markdown converter ai llm table-extraction image-analysis document-processing gemini openai",
"author": "Shorya Sethia",
"author_email": "shoryasethia4may@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/5e/c8/f62d5088b9a4e3ee1520f7cba3daefec8d0c74d4abf461cb94fc399e2932/markdrop-0.3.1.3.tar.gz",
"platform": null,
"description": "# MARKDROP\r\n\r\n<a href=\"https://pepy.tech/projects/markdrop\"><img src=\"https://static.pepy.tech/badge/markdrop\" alt=\"markdrop total downloads\"></a>\r\n\r\nA Python package for converting PDFs (or PDF URLs) to markdown while extracting images and tables, with advanced features for AI-powered content analysis and descriptions.\r\n\r\n## Features \r\n\r\n- [x] PDF to Markdown conversion with formatting preservation using Docling\r\n- [x] Automatic image extraction with quality preservation using XRef Id\r\n- [x] Table detection using Microsoft's Table Transformer\r\n- [x] PDF URL support for core functionalities\r\n- [x] AI-powered image and table descriptions using multiple LLM providers\r\n- [x] Interactive HTML output with downloadable Excel tables\r\n- [x] Customizable image resolution and UI elements\r\n- [x] Comprehensive logging system\r\n- [ ] Optical Character Recognition (OCR) for images with embedded text\r\n- [ ] Support for multi-language PDFs\r\n\r\n## Installation \r\n\r\n```bash \r\npip install markdrop \r\n``` \r\n\r\n> https://pypi.org/project/markdrop \r\n\r\n## Quick Start \r\n\r\n### Basic PDF Processing\r\n\r\n```python\r\nfrom markdrop import extract_images, make_markdown, extract_tables_from_pdf\r\n\r\nsource_pdf = 'url/or/path/to/pdf/file' # Replace with your local PDF file path or a URL\r\noutput_dir = 'data/output' # Replace with desired output directory's path\r\n\r\nmake_markdown(source_pdf, output_dir)\r\nextract_images(source_pdf, output_dir)\r\nextract_tables_from_pdf(source_pdf, output_dir=output_dir)\r\n```\r\n\r\n### Advanced PDF Processing with MarkDrop\r\n\r\n```python\r\nfrom markdrop import markdrop, MarkDropConfig, add_downloadable_tables\r\nfrom pathlib import Path\r\nimport logging\r\n\r\n# Configure processing options\r\nconfig = MarkDropConfig(\r\n image_resolution_scale=2.0, # Scale factor for image resolution\r\n download_button_color='#444444', # Color for download buttons in HTML\r\n log_level=logging.INFO, # Logging detail level\r\n log_dir='logs', # Directory for log files\r\n excel_dir='markdropped-excel-tables' # Directory for Excel table exports\r\n)\r\n\r\n# Process PDF document\r\ninput_doc_path = \"path/to/input.pdf\"\r\noutput_dir = Path('output_directory')\r\n\r\n# Convert PDF and generate HTML with images and tables\r\nhtml_path = markdrop(input_doc_path, output_dir, config)\r\n\r\n# Add interactive table download functionality\r\ndownloadable_html = add_downloadable_tables(html_path, config)\r\n```\r\n\r\n### AI-Powered Content Analysis\r\n\r\n```python\r\nfrom markdrop import setup_keys, process_markdown, ProcessorConfig, AIProvider\r\nfrom pathlib import Path\r\n\r\n# Set up API keys for AI providers\r\nsetup_keys(key='gemini') # or setup_keys(key='openai')\r\n\r\n# Configure AI processing options\r\nconfig = ProcessorConfig(\r\n input_path=\"path/to/markdown/file.md\", # Input markdown file path\r\n output_dir=Path(\"output_directory\"), # Output directory\r\n ai_provider=AIProvider.GEMINI, # AI provider (GEMINI or OPENAI)\r\n remove_images=False, # Keep or remove original images\r\n remove_tables=False, # Keep or remove original tables\r\n table_descriptions=True, # Generate table descriptions\r\n image_descriptions=True, # Generate image descriptions\r\n max_retries=3, # Number of API call retries\r\n retry_delay=2, # Delay between retries in seconds\r\n gemini_model_name=\"gemini-1.5-flash\", # Gemini model for images\r\n gemini_text_model_name=\"gemini-pro\", # Gemini model for text\r\n image_prompt=DEFAULT_IMAGE_PROMPT, # Custom prompt for image analysis\r\n table_prompt=DEFAULT_TABLE_PROMPT # Custom prompt for table analysis\r\n)\r\n\r\n# Process markdown with AI descriptions\r\noutput_path = process_markdown(config)\r\n```\r\n\r\n### Image Description Generation\r\n\r\n```python\r\nfrom markdrop import generate_descriptions\r\n\r\nprompt = \"Give textual highly detailed descriptions from this image ONLY, nothing else.\"\r\ninput_path = 'path/to/img_file/or/dir'\r\noutput_dir = 'data/output'\r\nllm_clients = ['gemini', 'llama-vision'] # Available: ['qwen', 'gemini', 'openai', 'llama-vision', 'molmo', 'pixtral']\r\n\r\ngenerate_descriptions(\r\n input_path=input_path,\r\n output_dir=output_dir,\r\n prompt=prompt,\r\n llm_client=llm_clients\r\n)\r\n```\r\n\r\n## API Reference \r\n\r\n### Core Functions\r\n\r\n#### markdrop(input_doc_path: str, output_dir: str, config: Optional[MarkDropConfig] = None) -> Path\r\nConverts PDF to markdown and HTML with enhanced features.\r\n\r\nParameters:\r\n- `input_doc_path` (str): Path to input PDF file\r\n- `output_dir` (str): Output directory path\r\n- `config` (MarkDropConfig, optional): Configuration options for processing\r\n\r\n#### add_downloadable_tables(html_path: Path, config: Optional[MarkDropConfig] = None) -> Path\r\nAdds interactive table download functionality to HTML output.\r\n\r\nParameters:\r\n- `html_path` (Path): Path to HTML file\r\n- `config` (MarkDropConfig, optional): Configuration options\r\n\r\n### Configuration Classes\r\n\r\n#### MarkDropConfig\r\nConfiguration for PDF processing:\r\n- `image_resolution_scale` (float): Scale factor for image resolution (default: 2.0)\r\n- `download_button_color` (str): HTML color code for download buttons (default: '#444444')\r\n- `log_level` (int): Logging level (default: logging.INFO)\r\n- `log_dir` (str): Directory for log files (default: 'logs')\r\n- `excel_dir` (str): Directory for Excel table exports (default: 'markdropped-excel-tables')\r\n\r\n#### ProcessorConfig\r\nConfiguration for AI processing:\r\n- `input_path` (str): Path to markdown file\r\n- `output_dir` (str): Output directory path\r\n- `ai_provider` (AIProvider): AI provider selection (GEMINI or OPENAI)\r\n- `remove_images` (bool): Whether to remove original images\r\n- `remove_tables` (bool): Whether to remove original tables\r\n- `table_descriptions` (bool): Generate table descriptions\r\n- `image_descriptions` (bool): Generate image descriptions\r\n- `max_retries` (int): Maximum API call retries\r\n- `retry_delay` (int): Delay between retries in seconds\r\n- `gemini_model_name` (str): Gemini model for image processing\r\n- `gemini_text_model_name` (str): Gemini model for text processing\r\n- `image_prompt` (str): Custom prompt for image analysis\r\n- `table_prompt` (str): Custom prompt for table analysis\r\n\r\n### Legacy Functions\r\n\r\n#### make_markdown(source: str, output_dir: str, verbose: bool = False)\r\nLegacy function for basic PDF to markdown conversion.\r\n\r\nParameters:\r\n- `source` (str): Path to input PDF or URL\r\n- `output_dir` (str): Output directory path\r\n- `verbose` (bool): Enable detailed logging\r\n\r\n#### extract_images(source: str, output_dir: str, verbose: bool = False)\r\nLegacy function for basic image extraction.\r\n\r\nParameters:\r\n- `source` (str): Path to input PDF or URL\r\n- `output_dir` (str): Output directory path\r\n- `verbose` (bool): Enable detailed logging\r\n\r\n#### extract_tables_from_pdf(pdf_path: str, **kwargs)\r\nLegacy function for basic table extraction.\r\n\r\nParameters:\r\n- `pdf_path` (str): Path to input PDF or URL\r\n- `start_page` (int, optional): Starting page number\r\n- `end_page` (int, optional): Ending page number\r\n- `threshold` (float, optional): Detection confidence threshold\r\n- `output_dir` (str): Output directory path\r\n\r\n## Contributing \r\n\r\nWe welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details. \r\n\r\n### Development Setup \r\n\r\n1. Clone the repository: \r\n```bash \r\ngit clone https://github.com/shoryasethia/markdrop.git \r\ncd markdrop \r\n``` \r\n\r\n2. Create a virtual environment: \r\n```bash \r\npython -m venv venv \r\nsource venv/bin/activate # On Windows: venv\\Scripts\\activate \r\n``` \r\n\r\n3. Install development dependencies: \r\n```bash \r\npip install -r requirements.txt \r\n``` \r\n\r\n## Project Structure \r\n\r\n```bash \r\nmarkdrop/ \r\n\u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac LICENSE \r\n\u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac README.md \r\n\u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac CONTRIBUTING.md \r\n\u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac CHANGELOG.md \r\n\u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac requirements.txt \r\n\u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac setup.py \r\n\u00e2\u201d\u201d\u00e2\u201d\u20ac\u00e2\u201d\u20ac markdrop/ \r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac __init__.py \r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac src\r\n | \u00e2\u201d\u201d\u00e2\u201d\u20ac\u00e2\u201d\u20ac markdrop-logo.png\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac main.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac process.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac api_setup.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac parse.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac utils.py \r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac helper.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac ignore_warnings.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac run.py\r\n \u00e2\u201d\u201d\u00e2\u201d\u20ac\u00e2\u201d\u20ac models/\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac __init__.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac .env\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac img_descriptions.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac logger.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac model_loader.py\r\n \u00e2\u201d\u0153\u00e2\u201d\u20ac\u00e2\u201d\u20ac responder.py\r\n \u00e2\u201d\u201d\u00e2\u201d\u20ac\u00e2\u201d\u20ac setup_keys.py \r\n``` \r\n\r\n## License \r\n\r\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. \r\n\r\n## Changelog \r\n\r\nSee [CHANGELOG.md](CHANGELOG.md) for version history. \r\n\r\n## Code of Conduct \r\n\r\nPlease note that this project follows our [Code of Conduct](CODE_OF_CONDUCT.md). \r\n\r\n## Support \r\n\r\n- [Open an issue](https://github.com/shoryasethia/markdrop/issues)\r\n",
"bugtrack_url": null,
"license": null,
"summary": "A comprehensive PDF processing toolkit that converts PDFs to markdown with advanced AI-powered features for image and table analysis. Supports local files and URLs, preserves document structure, extracts high-quality images, detects tables using advanced ML models, and generates detailed content descriptions using multiple LLM providers including OpenAI and Google's Gemini.",
"version": "0.3.1.3",
"project_urls": {
"Homepage": "https://github.com/shoryasethia/markdrop"
},
"split_keywords": [
"pdf",
"markdown",
"converter",
"ai",
"llm",
"table-extraction",
"image-analysis",
"document-processing",
"gemini",
"openai"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "043e4e1a5d73dc50e31fbbf473e7af477c2cb3efc75d45f383988fbf15c8e763",
"md5": "91dc647fe67c07e062c9f835b8b3f626",
"sha256": "4222783602ceddc85410c9a614bbde1deadba7d456da90b6218ef3055b4e7abf"
},
"downloads": -1,
"filename": "markdrop-0.3.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "91dc647fe67c07e062c9f835b8b3f626",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 30475,
"upload_time": "2025-01-29T22:37:56",
"upload_time_iso_8601": "2025-01-29T22:37:56.777239Z",
"url": "https://files.pythonhosted.org/packages/04/3e/4e1a5d73dc50e31fbbf473e7af477c2cb3efc75d45f383988fbf15c8e763/markdrop-0.3.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5ec8f62d5088b9a4e3ee1520f7cba3daefec8d0c74d4abf461cb94fc399e2932",
"md5": "6c83611c284f2fe738b5dedf19cdc5e5",
"sha256": "9b41d0f33d08052c26db53eeb9121466e4e8cc80390c1002b138347937dc63b0"
},
"downloads": -1,
"filename": "markdrop-0.3.1.3.tar.gz",
"has_sig": false,
"md5_digest": "6c83611c284f2fe738b5dedf19cdc5e5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 28753,
"upload_time": "2025-01-29T22:37:58",
"upload_time_iso_8601": "2025-01-29T22:37:58.330069Z",
"url": "https://files.pythonhosted.org/packages/5e/c8/f62d5088b9a4e3ee1520f7cba3daefec8d0c74d4abf461cb94fc399e2932/markdrop-0.3.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-29 22:37:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "shoryasethia",
"github_project": "markdrop",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "beautifulsoup4",
"specs": []
},
{
"name": "beautifulsoup4",
"specs": []
},
{
"name": "docling",
"specs": []
},
{
"name": "docling_core",
"specs": [
[
"==",
"2.16.0"
]
]
},
{
"name": "openai",
"specs": []
},
{
"name": "openpyxl",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "Pillow",
"specs": []
},
{
"name": "protobuf",
"specs": []
},
{
"name": "python-dotenv",
"specs": []
},
{
"name": "pymupdf",
"specs": []
},
{
"name": "torch",
"specs": []
},
{
"name": "tqdm",
"specs": []
},
{
"name": "transformers",
"specs": []
},
{
"name": "timm",
"specs": []
},
{
"name": "requests",
"specs": []
},
{
"name": "qwen_vl_utils",
"specs": []
},
{
"name": "google.generativeai",
"specs": []
},
{
"name": "vllm",
"specs": []
},
{
"name": "openai",
"specs": []
},
{
"name": "setuptools",
"specs": []
},
{
"name": "typing",
"specs": []
}
],
"lcname": "markdrop"
}
JSON
