Metadata-Version: 2.4
Name: trust-sense
Version: 0.1.1
Summary: Advanced Multimodal AI Library for Fake News & Psyops Detection
Author-email: Codisa <codisiast@gmail.com>
Maintainer-email: Codisa <codisiast@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/trust-sense/trust-sense
Project-URL: Documentation, https://github.com/trust-sense/trust-sense#readme
Project-URL: Repository, https://github.com/trust-sense/trust-sense
Project-URL: Bug Tracker, https://github.com/trust-sense/trust-sense/issues
Project-URL: Changelog, https://github.com/trust-sense/trust-sense/releases
Project-URL: Source Code, https://github.com/trust-sense/trust-sense
Keywords: fake-news,fake news detection,misinformation,disinformation,psyops,psychological operations,manipulation detection,trust analysis,credibility assessment,multimodal analysis,fact-checking,NLP,computer vision,audio analysis,media analysis,information security,integrity verification
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
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: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Security
Classifier: Topic :: Multimedia
Classifier: Topic :: Internet :: WWW/HTTP
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.26.0
Requires-Dist: scikit-learn>=1.4.0
Requires-Dist: pillow>=10.0.0
Requires-Dist: requests>=2.31.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: pydantic>=2.0.0
Provides-Extra: torch
Requires-Dist: torch>=2.2.0; extra == "torch"
Provides-Extra: transformers
Requires-Dist: transformers>=4.40.0; extra == "transformers"
Provides-Extra: full
Requires-Dist: torch>=2.2.0; extra == "full"
Requires-Dist: transformers>=4.40.0; extra == "full"
Requires-Dist: opencv-python-headless>=4.9.0; extra == "full"
Requires-Dist: librosa>=0.10.0; extra == "full"
Requires-Dist: soundfile>=0.12.1; extra == "full"
Requires-Dist: sounddevice>=0.4.6; extra == "full"
Requires-Dist: pytesseract>=0.3.10; extra == "full"
Requires-Dist: deepface>=0.0.79; extra == "full"
Requires-Dist: speechrecognition>=3.10.0; extra == "full"
Requires-Dist: pytrends>=4.9.0; extra == "full"
Requires-Dist: datasets>=2.0.0; extra == "full"
Requires-Dist: accelerate>=0.12.0; extra == "full"
Requires-Dist: pytorch-lightning>=1.8.0; extra == "full"
Provides-Extra: gpu
Requires-Dist: torch>=2.2.0; extra == "gpu"
Requires-Dist: cuda-python>=11.0; extra == "gpu"
Provides-Extra: api
Requires-Dist: fastapi>=0.110.0; extra == "api"
Requires-Dist: uvicorn[standard]>=0.29.0; extra == "api"
Requires-Dist: slowapi>=0.1.9; extra == "api"
Requires-Dist: python-pptx>=0.6.23; extra == "api"
Requires-Dist: websockets>=12.0; extra == "api"
Requires-Dist: aiofiles>=23.2.1; extra == "api"
Requires-Dist: tomli>=2.0.1; extra == "api"
Provides-Extra: dev
Requires-Dist: pytest>=6.0.0; extra == "dev"
Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: black>=21.0.0; extra == "dev"
Requires-Dist: flake8>=3.9.0; extra == "dev"
Requires-Dist: mypy>=0.800; extra == "dev"
Requires-Dist: isort>=5.0.0; extra == "dev"
Requires-Dist: pre-commit>=2.15.0; extra == "dev"
Provides-Extra: docs
Requires-Dist: sphinx>=4.0.0; extra == "docs"
Requires-Dist: sphinx-rtd-theme>=1.0.0; extra == "docs"
Requires-Dist: sphinx-autodoc-typehints>=1.12.0; extra == "docs"
Dynamic: license-file

# Trust Sense

> **Advanced Multimodal AI Library for Fake News & Psyops Detection**

[![PyPI version](https://badge.fury.io/py/trust-sense.svg)](https://pypi.org/project/trust-sense/)
[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

A powerful Python library for detecting fake news, psychological operations, propaganda, and manipulated media.

## 🚀 Quick Start

```python
from trust_sense import detect_fake_news, detect_psyops

# Detect fake news
is_fake = detect_fake_news("Breaking: Scientists discover cure for aging!")
print(f"Fake news detected: {is_fake}")

# Detect psyops/manipulation
is_psyops = detect_psyops("URGENT!!! SHARE THIS NOW OR YOU'LL REGRET IT!!!")
print(f"Psyops detected: {is_psyops}")
```

## 📦 Installation

```bash
# Basic installation
pip install trust-sense

# Full features with ML models
pip install trust-sense[full]

# API server support
pip install trust-sense[api]

# Development tools
pip install trust-sense[dev]
```

## 🎯 Features

- **Text Analysis**: Detect fake news, manipulation, and propaganda
- **Audio Analysis**: Emotion detection and credibility assessment
- **Video Analysis**: Deepfake detection and facial analysis
- **Multimodal**: Combined analysis across multiple data types
- **Lazy Loading**: Optional dependencies loaded only when needed
- **Graceful Fallback**: Works without heavy ML models

## 💡 Usage Examples

### Quick Detection Functions

```python
from trust_sense import detect_fake_news, detect_psyops, analyze_trust

# Simple fake news detection
is_fake = detect_fake_news("Breaking: UFO lands in Times Square!")

# Psychological operations detection
is_psyops = detect_psyops("SHARE THIS OR THEY'LL HIDE THE TRUTH!!!")

# Comprehensive analysis
analysis = analyze_trust("Some suspicious content...")
print(f"Risk Level: {analysis['risk_level']}")
```

### Advanced Usage with Detector Classes

```python
from trust_sense import FakeNewsDetector, PsyopsDetector, TrustAnalyzer

# Fake news detector
detector = FakeNewsDetector()
result = detector.analyze("Article text...")
print(f"Confidence: {result.confidence:.2%}")
print(f"Risk Level: {result.risk_level}")

# Psyops detector
psyops = PsyopsDetector()
result = psyops.analyze("Manipulative content...")
print(f"Techniques: {result.techniques}")
```

### API Server

```python
from trust_sense import TrustAPI

# Start API server
api = TrustAPI(host='0.0.0.0', port=8000)
api.run()

# Visit: http://localhost:8000/docs for interactive API docs
```

## 📚 Documentation

For detailed API reference and advanced usage, see:
- Package documentation in `docs/trust_sense_documentation.tex` (LaTeX source)
- Examples in `trust_sense/examples/` directory
- API server documentation at `http://localhost:8000/docs` when running the server

## 🧪 Testing

```bash
# Install development dependencies
pip install trust-sense[dev]

# Run tests
pytest

# Run with coverage
pytest --cov=trust_sense
```

## 🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

## 📄 License

MIT License - see [LICENSE](LICENSE) file

## �‍💻 Author

**Created by Codisa**

## �📞 Support

- **Issues**: https://github.com/codisia/trust-sense/issues
- **Email**: codisiast@gmail.com
- **Documentation**: https://github.com/codisia/trust-sense#readme

---

**Version**: 0.1.0  
**Python**: >= 3.8  
