waylay-ml-adapter-api 0.1.0

API models for the ml-adapter.

waylay-ml-adapter-api

Provides the ml_adapter.api module for the Waylay ML Adapter solution.

This module is not meant to be used on its own.

To use an ML Adapter in a Waylay plugin or webscript, use the adapter relevant to your machine learning framework:

• waylay-ml-adapter-numpy for generic models that use numpy data representation
• waylay-ml-adapter-sklearn for scikit-learn models.
• waylay-ml-adapter-torch for pytorch models.

The waylay-ml-adapter-base module provides a basis to create adapters for other frameworks.

The waylay-ml-adapter-sdk module provides the ml_tool extension to the waylay-sdk SDK. It helps to create and test adapters from e.g. a python notebook.

Classes exported by ml_adapter.api

The module ml_adapter.api exports the following classes

v1

V1 Dataplane protocol for ML services.

See

• KServe V1
• Tensorflow V1

v2

V2 Dataplane protocol for ML services.

See

• Open Inference Protocol