Metadata-Version: 2.2
Name: superllm
Version: 0.1.0
Summary: Enhanced LLM capabilities through test-time compute and search algorithms
Home-page: https://github.com/to314as/superllm
Author: SuperLLM Contributors
Author-email: SuperLLM Contributors <tobias.oberkofler@lmu.de>
License: GPLv3
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.20.0
Requires-Dist: torch>=2.0.0
Requires-Dist: transformers>=4.30.0
Requires-Dist: networkx>=2.8.0
Requires-Dist: tqdm>=4.65.0
Requires-Dist: scipy>=1.8.0
Requires-Dist: pandas>=1.5.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
Requires-Dist: black>=22.0.0; extra == "dev"
Requires-Dist: isort>=5.0.0; extra == "dev"
Requires-Dist: flake8>=4.0.0; extra == "dev"
Requires-Dist: mypy>=0.900; extra == "dev"
Requires-Dist: build>=1.0.0; extra == "dev"
Requires-Dist: twine>=4.0.0; extra == "dev"
Requires-Dist: sphinx>=7.0.0; extra == "dev"
Requires-Dist: sphinx-rtd-theme>=1.3.0; extra == "dev"
Requires-Dist: sphinx-autodoc-typehints>=1.25.0; extra == "dev"
Requires-Dist: myst-parser>=2.0.0; extra == "dev"
Dynamic: author
Dynamic: home-page
Dynamic: requires-python

# SuperLLM

A powerful Python library for enhancing LLM capabilities through advanced test-time compute and search algorithms, focusing on expert human-AI co-construction.
This project is under consturction. Don't come with any expectations!

## 🌟 Features

- **Test-Time Compute Algorithms**
  - Tree of Thoughts implementation
  - Self-consistency sampling
  - Dynamic prompt optimization
  - Multi-perspective reasoning

- **Search Algorithms**
  - Beam search with adaptive width
  - Best-first symbolic search
  - Guided exploration with expert feedback
  - Knowledge graph-based reasoning

- **Expert Human-AI Co-Construction**
  - Interactive reasoning frameworks
  - Expert feedback integration
  - Knowledge distillation from expert interactions
  - Adaptive learning from human guidance

## 🚀 Installation

```bash
pip install superllm
```

## 🔧 Quick Start

```python
from superllm import ThoughtTree, ExpertFeedback
from superllm.search import AdaptiveBeamSearch

# Initialize a thought tree for complex reasoning
thought_tree = ThoughtTree()

# Create an expert feedback system
expert_system = ExpertFeedback()

# Configure adaptive beam search
search = AdaptiveBeamSearch(
    beam_width=5,
    max_steps=10
)

# Run enhanced inference
result = thought_tree.solve(
    prompt="Your complex question here",
    search_algorithm=search,
    expert_system=expert_system
)
```

## 📚 Documentation

For detailed documentation, visit [docs.superllm.ai](https://docs.superllm.ai)

## 🛠️ Core Components

1. **Thought Trees**: Implement tree-based reasoning strategies for complex problem-solving
2. **Search Algorithms**: Advanced search techniques for exploring solution spaces
3. **Expert Systems**: Tools for integrating human expert knowledge and feedback
4. **Evaluation Metrics**: Comprehensive metrics for assessing solution quality

## 🤝 Contributing

We welcome contributions! Please check our [Contributing Guidelines](CONTRIBUTING.md) for details.

## 📄 License

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

## 🔗 Citation

If you use SuperLLM in your research, please cite:

```bibtex
@software{superllm2024,
  title = {SuperLLM: Enhanced LLM Capabilities through Test-Time Compute},
  author = {SuperLLM Contributors},
  year = {2024},
  url = {https://github.com/to314as/superllm}
}
```

## 🌟 Star History

[![Star History Chart](https://api.star-history.com/svg?repos=to314as/superllm&type=Date)](https://star-history.com/#to314as/superllm&Date)
