Example

This example demonstrates how to use this AI & ML Agent to call a machine learning model deployed in Azure.

Refer to configuration to understand all configuration options of this Agent.

Step 1: Add the Agent

Drag the Azure ML Agent onto the canvas, link the input endpoint to the iris flower dataset and the output to the printer. Rename the Agent and save the Data Stream.

Step 2: Configure General

Select the Agent and click Configure. Keep the default Collection.

Step 3: Configure Machine Learning Model

Tick to use variables and select the URL and API key. Apply the changes and save the Data Stream.

Step 4: Input Mapping

Select the Azure ML's input arrow and click Configure.

Map one of the parent Agent's output attributes to each training attribute, which is fetched from the Azure model.

Step 5: Results

Apply the changes, save the Data Stream, and publish it.

Let's look at the Live Data View. The Azure model returns a predicted value based on the input iris data - this score and timestamp are appended to the iris data and printed.

Files

See the Import, Export, and Clone - XMPro article for steps to import a Data Stream.

Last updated