Azure ML

Supported Labeling Types: Row Labeling

To ensure seamless integration, we have created a direct integration with the Azure model. We understand that most of our clients have existing data and training pipelines in Azure, so we allow you to use your trained model directly to improve its performance.

To use the Azure model, you need to select Azure as the Settings option. Once selected, you will see the menu below:

ML Assisted with Azure

1. Target text: Pick which text to use as input for reference.

2. Target question: Decide which output column to predict.

3. API URL: The endpoint built in Azure AutoML.

4. API token: The user's token that allows other applications to communicate with the model.

5. Faster prediction speed: Toggle this option to run predictions faster via the backend.

To obtain the API URL and API token, you should enable authentication when building the models during this step. Once deployed, you will receive the REST endpoint as your API URL and the authentication token as your API token.

After configuring the above options, you can predict the labels and get the predicted labels from your own model.