Metadata-Version: 2.4
Name: llama-d5
Version: 0.1.0
Summary: A comprehensive document and web page conversion toolkit powered by Llama AI
Project-URL: Homepage, https://github.com/llama-ai/llama-d5
Project-URL: Bug Tracker, https://github.com/llama-ai/llama-d5/issues
Author-email: Llama D5 Team <team@llamad5.dev>
License: MIT License
        
        Copyright (c) 2024 Llama AI
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE. 
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Documentation
Classifier: Topic :: Internet :: WWW/HTTP :: Browsers
Classifier: Topic :: Text Processing
Classifier: Topic :: Utilities
Requires-Python: >=3.8
Requires-Dist: aiohttp>=3.8.3
Requires-Dist: alembic>=1.12.0
Requires-Dist: anticaptchaofficial>=1.0.54
Requires-Dist: beautifulsoup4>=4.12.2
Requires-Dist: cloudscraper>=1.2.60
Requires-Dist: docx2pdf>=0.1.8
Requires-Dist: fake-useragent>=1.1.1
Requires-Dist: fastapi>=0.104.0
Requires-Dist: img2pdf>=0.5.0
Requires-Dist: langchain>=0.0.267
Requires-Dist: llama-index-tools-playwright>=0.1.0
Requires-Dist: llm-cmd>=0.1.0
Requires-Dist: llm-mlx>=0.2.0
Requires-Dist: markdown2>=2.4.6
Requires-Dist: markdown>=3.5.1
Requires-Dist: mlx>=0.8.0
Requires-Dist: networkx>=3.2
Requires-Dist: numpy>=1.24.2
Requires-Dist: openai>=1.0.0
Requires-Dist: opencv-python-headless>=4.7.0.68
Requires-Dist: pdfkit>=1.0.0
Requires-Dist: pikepdf>=6.2.5
Requires-Dist: pillow>=10.0.0
Requires-Dist: playwright-pdf>=0.1.3
Requires-Dist: playwright-stealth>=1.0.7
Requires-Dist: playwright>=1.40.0
Requires-Dist: pydantic-settings>=2.0.3
Requires-Dist: pydantic>=2.4.2
Requires-Dist: pypdf2>=2.12.1
Requires-Dist: pypdf>=4.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: reportlab>=4.0.4
Requires-Dist: requests-html>=0.10.0
Requires-Dist: requests>=2.31.0
Requires-Dist: rich>=13.0.0
Requires-Dist: selenium-stealth>=1.0.6
Requires-Dist: selenium>=4.8.0
Requires-Dist: setuptools>=68.0.0
Requires-Dist: shot-scraper>=0.9.0
Requires-Dist: sqlalchemy>=2.0.23
Requires-Dist: tf-playwright-stealth>=0.1.0
Requires-Dist: tqdm>=4.66.1
Requires-Dist: typer>=0.9.0
Requires-Dist: undetected-chromedriver>=3.2.0
Requires-Dist: uvicorn>=0.23.2
Requires-Dist: weasyprint>=60.1
Provides-Extra: all
Requires-Dist: black>=23.10.1; extra == 'all'
Requires-Dist: flake8>=6.1.0; extra == 'all'
Requires-Dist: isort>=5.12.0; extra == 'all'
Requires-Dist: mypy>=1.6.1; extra == 'all'
Requires-Dist: pre-commit>=3.5.0; extra == 'all'
Requires-Dist: pytest-cov>=4.1.0; extra == 'all'
Requires-Dist: pytest-mock>=3.12.0; extra == 'all'
Requires-Dist: pytest-playwright-asyncio>=0.7.0; extra == 'all'
Requires-Dist: pytest-playwright>=0.7.0; extra == 'all'
Requires-Dist: pytest-sugar>=0.9.7; extra == 'all'
Requires-Dist: pytest>=7.4.3; extra == 'all'
Requires-Dist: ruff>=0.0.260; extra == 'all'
Requires-Dist: tox>=4.11.3; extra == 'all'
Requires-Dist: uv>=0.1.0; extra == 'all'
Provides-Extra: dev
Requires-Dist: black>=23.10.1; extra == 'dev'
Requires-Dist: flake8>=6.1.0; extra == 'dev'
Requires-Dist: isort>=5.12.0; extra == 'dev'
Requires-Dist: mypy>=1.6.1; extra == 'dev'
Requires-Dist: pre-commit>=3.5.0; extra == 'dev'
Requires-Dist: pytest-cov>=4.1.0; extra == 'dev'
Requires-Dist: pytest-mock>=3.12.0; extra == 'dev'
Requires-Dist: pytest-playwright-asyncio>=0.7.0; extra == 'dev'
Requires-Dist: pytest-playwright>=0.7.0; extra == 'dev'
Requires-Dist: pytest-sugar>=0.9.7; extra == 'dev'
Requires-Dist: pytest>=7.4.3; extra == 'dev'
Requires-Dist: ruff>=0.0.260; extra == 'dev'
Requires-Dist: tox>=4.11.3; extra == 'dev'
Requires-Dist: uv>=0.1.0; extra == 'dev'
Description-Content-Type: text/markdown

# llama-d5

[![PyPI version](https://img.shields.io/pypi/v/llama_d5.svg)](https://pypi.org/project/llama_d5/)
[![License](https://img.shields.io/github/license/llamasearchai/llama-d5)](https://github.com/llamasearchai/llama-d5/blob/main/LICENSE)
[![Python Version](https://img.shields.io/pypi/pyversions/llama_d5.svg)](https://pypi.org/project/llama_d5/)
[![CI Status](https://github.com/llamasearchai/llama-d5/actions/workflows/llamasearchai_ci.yml/badge.svg)](https://github.com/llamasearchai/llama-d5/actions/workflows/llamasearchai_ci.yml)

**Llama D5 (llama-d5)** is a document processing toolkit within the LlamaSearch AI ecosystem. It appears to focus on document conversion (potentially from various formats to PDF, indicated by `llamadoc2pdf`) and capturing document representations (like screenshots, suggested by `llama_screenshot`).

## Key Features

- **Document Conversion:** Includes components for converting document formats, possibly centered around PDF output (`llamadoc2pdf/`).
- **Document Capture:** Functionality to capture visual representations of documents, like screenshots (`llama_screenshot.py`).
- **Core Module:** Likely orchestrates the conversion and capture processes (`core.py`).
- **Configurable:** Supports configuration options (`config.py`).

## Installation

```bash
pip install llama-d5
# Or install directly from GitHub for the latest version:
# pip install git+https://github.com/llamasearchai/llama-d5.git
```

## Usage

*(Usage examples for document conversion and screenshot generation will be added here.)*

```python
# Placeholder for Python client usage
# from llama_d5 import DocProcessor, ConversionConfig

# config = ConversionConfig.load("config.yaml")
# processor = DocProcessor(config)

# # Convert a document to PDF
# pdf_path = processor.convert_to_pdf(input_file="document.docx")
# print(f"PDF saved to: {pdf_path}")

# # Take a screenshot
# screenshot_path = processor.take_screenshot(url="https://example.com", output_file="webpage.png")
# print(f"Screenshot saved to: {screenshot_path}")
```

## Architecture Overview

```mermaid
graph TD
    A[Input Document / URL] --> B{Core Processor (core.py)};
    B -- Conversion Task --> C{Document Converter (llamadoc2pdf/)};
    C --> D[Output PDF];
    B -- Capture Task --> E{Screenshot Tool (llama_screenshot.py)};
    E --> F[Output Image (Screenshot)];

    G[Configuration (config.py)] -- Configures --> B;
    G -- Configures --> C;
    G -- Configures --> E;

    style B fill:#f9f,stroke:#333,stroke-width:2px
```

1.  **Input:** Accepts a document file or URL.
2.  **Core Processor:** Manages the request and routes it to the appropriate tool.
3.  **Converter:** Handles conversion of input documents into PDF format.
4.  **Screenshot Tool:** Captures a visual representation (screenshot) of a document or webpage.
5.  **Output:** Produces either a PDF file or an image file.
6.  **Configuration:** Settings control the behavior of the conversion and capture tools.

## Configuration

*(Details on configuring input/output formats, screenshot resolution, conversion options, etc., will be added here.)*

## Development

### Setup

```bash
# Clone the repository
git clone https://github.com/llamasearchai/llama-d5.git
cd llama-d5

# Install in editable mode with development dependencies
pip install -e ".[dev]"
```

### Testing

```bash
pytest tests/
```

### Contributing

Contributions are welcome! Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) and submit a Pull Request.

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
