After you train your model and you're happy with the model performance, use the model in your app logic.
To use the model in your app, you need to:
- Install the ML Builder plugin. You can download the plugin during the setup, as described in Getting started.
- Deploy at least one model. You can deploy a model by clicking on the Deploy button in the model overview page.
In Service Studio, open the app where you want to implement the model and do the following:
- Reference the ML Builder plugin. Press Ctrl+Q and in the Manage Dependencies window search for
MLBuilderPlugin. Then, select the Service Actions in the right pane.
In the logic of your app, use the Actions from Logic > Service Actions > MLBuilderPlugin > ModelScore to get the scores from your models:
- GetAttributePrediction for attribute models
- GetTextClassification for text classification models
Explore the parameters of the actions to learn more about the values they require and return.
ML Builder is currently in a public early access program (EAP) and you need to register at the ML Builder registration page to try it out.