https://github.com/sebiwtt/delta
A tool for deploying and managing online ML models via a microservice architecture, enabling dynamic and scalable machine learning operations.
https://github.com/sebiwtt/delta
machine-learning online-ml river
Last synced: 6 months ago
JSON representation
A tool for deploying and managing online ML models via a microservice architecture, enabling dynamic and scalable machine learning operations.
- Host: GitHub
- URL: https://github.com/sebiwtt/delta
- Owner: sebiwtt
- License: bsd-3-clause
- Created: 2024-03-01T17:47:57.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-03-01T17:54:07.000Z (over 2 years ago)
- Last Synced: 2024-03-05T15:54:05.596Z (over 2 years ago)
- Topics: machine-learning, online-ml, river
- Homepage:
- Size: 4.88 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Delta🌊🔀
DeltaMLOps is an innovative tool designed for the efficient deployment and management of online machine learning models, specifically tailored for integration with the River library. It utilizes a microservice architecture, allowing for dynamic and scalable operations in machine learning workflows.
## Features 🚀
- **Microservice-Based**: Each ML model functions as an independent microservice.
- **Dual API System**: Includes a public API for training and inference, and a management API for configuration and monitoring.
- **Dynamic Model Configuration**: Easily configurable models at runtime, adaptable to changing data streams.
- **Containerized Deployment**: Utilizes Docker for consistent and easy deployment, with Kubernetes support for scaling.
## Getting Started
### Prerequisites
- Docker
- Python 3.8+
- River 0.21.0
### Installation
### Quickstart
```python
# Quickstart guide with code snippets
```
## Usage
```python
# Example usage code
```
## Contributing
Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are **greatly appreciated**.
1. Fork the Project
2. Create your Feature Branch (`git checkout -b feature/yourFeature`)
3. Commit your Changes (`git commit -m 'Add some Feature'`)
4. Push to the Branch (`git push origin feature/yourFeature`)
5. Open a Pull Request
## License
Distributed under the BSD License. See `LICENSE` for more information.
## Contact
Sebastian Wette - mail@sebastianwette.de