Vertex AI - Predict task

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

The Vertex AI - Predict task lets you perform an online prediction. Online predictions are synchronous requests made to a model endpoint. You can use online predictions when making requests in response to application inputs or when you require timely inferences.

Vertex AI is a Google Cloud service that allows you to train and deploy ML models and AI applications, and customize large language models (LLMs) for use in your AI-powered applications.

Before you begin

Ensure that you perform the following tasks in your Google Cloud project before configuring the Vertex AI - Predict task:

1. Enable the Vertex AI API (aiplatform.googleapis.com).

   Enable the Vertex AI API

2. Deploy the model resource to the endpoint.
3. Create an authentication profile. Apigee Integration uses an authentication profile to connect to an authentication endpoint for the Vertex AI - Predict task.
   Note: If you're creating an authentication profile of Service account type, then ensure that the service account is assigned with the IAM role that contains the following IAM permission(s):

   • aiplatform.endpoints.predict

   To know about IAM permissions and the predefined IAM roles that grant them, see IAM permissions reference.

   For information about granting additional roles or permissions to a service account, see Granting, changing, and revoking access.

4. Ensure that VPC Service Controls is NOT setup for Apigee Integration in your Google Cloud project.
   Warning: Vertex AI - Predict task will not function or will stop functioning if VPC Service Controls is setup for Apigee Integration in your Google Cloud project.

Configure the Vertex AI - Predict task

1. In the Apigee UI, select your Apigee Organization.
2. Click Develop > Integrations.
3. Select an existing integration or create a new integration by clicking Create Integration.

   If you are creating a new integration:

   1. Enter a name and description in the Create Integration dialog.
   2. Select a Region for the integration from the list of supported regions.
   3. Click Create.

   This opens the integration in the integration designer.

4. In the integration designer navigation bar, click +Add a task/trigger > Tasks to view the list of available tasks.
5. Click and place the Vertex AI - Predict element in the integration designer.
6. Click the Vertex AI - Predict element on the designer to view the Vertex AI - Predict task configuration pane.
7. Go to Authentication, and select an existing authentication profile that you want to use.

   Optional. If you have not created an authentication profile prior to configuring the task, Click + New authentication profile and follow the steps as mentioned in Create a new authentication profile.

8. Go to Task Input, and configure the displayed inputs fields using the following Task input parameters table.

   Changes to the inputs fields are saved automatically.

Task input parameters

The following table describes the input parameters of the Vertex AI - Predict task:

Property	Data type	Description
Region	String	Model endpoint location. For example: us - United States.
ProjectsId	String	Your Google Cloud project ID.
Endpoint	String	The name of the endpoint requested to serve the prediction.
Request	JSON	See request JSON structure.

Task output

The Vertex AI - Predict task returns a response containing the prediction.

Error handling strategy

An error handling strategy for a task specifies the action to take if the task fails due to a temporary error. For information about how to use an error handling strategy, and to know about the different types of error handling strategies, see Error handling strategies.

What's next

1. Add edges and edge conditions.
2. Test and publish your integration.
3. Configure a trigger.
4. Add a Data Mapping task.
5. See all tasks for Google Cloud services.