Model Repository and Model Stores

A model store can be used to persist the trained graph server (PGX) machine learning models along with a model name (a unique identifier of the model in a particular model store) and a description.

The model repository API provides the following capabilities:

• Create a new model store

• List all the available model stores in the model repository

• Store a model in the model store

• List all the models in a given model store

• Load a model from the model store

• Get the model description for a model that is stored in the given model store

• Delete a model from the given model store

• Delete the existing model stores

• Database-Backed Model Repository