https://github.com/phidlarkson/llocaly
A streamlit-based interface for interacting with local AI models through Ollama.
https://github.com/phidlarkson/llocaly
ollama-interface open-source streamlit
Last synced: 3 months ago
JSON representation
A streamlit-based interface for interacting with local AI models through Ollama.
- Host: GitHub
- URL: https://github.com/phidlarkson/llocaly
- Owner: PhidLarkson
- Created: 2025-01-11T10:41:05.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-30T10:14:18.000Z (over 1 year ago)
- Last Synced: 2025-01-30T11:23:55.261Z (over 1 year ago)
- Topics: ollama-interface, open-source, streamlit
- Language: Python
- Homepage:
- Size: 9.77 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# llocaly
A streamlit-based interface for interacting with local AI models through Ollama.
## 🚀 Features
- **Local Model Integration**: Seamless interaction with locally hosted models via Ollama
- **System Monitoring**: CPU, RAM, and GPU data
- **Performance Metrics**: Track response times and token generation rates
- **Modern Interface**: Clean, minimalist design with a professional dark theme
- **Export Capabilities**: Save your chat sessions and performance data
## 📋 Prerequisites
- Python 3.8+
- Ollama installed and running on your system
- Good GPU (optional, models run with CPU too)
## 🛠️ Installation
1. Clone the repository:
```bash
git clone https://github.com/PhidLarkson/llocaly.git
cd llocaly
```
2. Install required packages:
```bash
pip install -r requirements.txt
```
3. Run the application:
```bash
streamlit run app.py
```
## 🤝 Contributing
We welcome contributions! llocaly is open for improvements, particularly in these areas:
### Priority Areas for Contribution
1. **Memory Management**
- Implement persistent conversation memory
- Add conversation context management
- Develop memory optimization strategies
2. **Model Integration**
- Expand support for different model formats
- Improve model loading and switching
- Add model performance benchmarking
3. **UI/UX Improvements**
- Enhanced visualization of system metrics
- Customizable themes
- Responsive design improvements
### How to Contribute
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to the branch (`git push origin feature/AmazingFeature`)
5. Open a Pull Request
## ⚙️ Configuration
The application can be configured through the sidebar interface:
- Model selection
- Temperature adjustment
- Context length settings
- System monitoring
## 📝 License
Distributed under the MIT License. See `LICENSE` for more information.
## 🙏 Acknowledgments
- [Ollama](https://ollama.com/) for local model serving
- [Streamlit](https://streamlit.io/) for the web interface
- Future contributors and supporters of the project
## 🔮 Future Plans
- Conversation memory persistence
- Multi-model chat sessions
- Advanced prompt templates
- Custom model configuration
- Performance optimization tools
- Framework variety
## ⚠️ Known Limitations
- Currently no persistent memory between sessions
- Limited to models available through Ollama
- Single conversation context at a time
## 📞 Support
For support, please open an issue in the GitHub repository.