Python framework for production ML systems.
modelkit is a Python framework to maintain and run machine learning (ML) code in production environments.
The key features are:
- type-safe Models' inputs and outputs can be validated by pydantic
- composable Models are composable: they can depend on other models.
- organized Store and share your models as regular Python packages.
- extensible Models can rely on arbitrary supporting configurations files called assets hosted on local or cloud object stores
- testable Models carry their own unit test cases, and unit testing fixtures are available for pytest
- fast to code Models can be served in a single CLI call using fastapi
- fast Models' predictions can be batched for speed
- async Models support async and synchronous prediction functions
Install with pip:
pip install modelkit
Refer to the documentation for more information.