Enable model event notification with Cloud Functions and Pub/Sub

1. Listen to the model data and generate events from it using Cloud Run functions.
2. Send the Cloud Run functions generated events through the Pub/Sub event channel.

Supported models

The following models offer Cloud Run functions event generation and Pub/Sub event notification integrations:

• Occupancy analytics model
• Vertex AI custom-trained models

Before you begin

• Create an app with, at minimum, a stream node and a supported model node.
• Optional. Install the Vertex AI Vision SDK and ingest data into your app. If you don't do this before you set up event notification you must do it after.
• Optional. Create a Cloud Run function to use. If you don't create your Cloud Run function before you configure Cloud Run functions to process model output, you must create it during that process.
• Optional. Create a Pub/Sub topic to use. If you don't create your Pub/Sub topic before you enable model event notification with Pub/Sub, you must create it during that process.
• Optional. Choose and create a Pub/Sub subscription. If you don't create your Pub/Sub subscription before you enable model event notification with Pub/Sub, you must create it after to read messages from a topic.

Configure Cloud Run functions to process model output

To trigger event-based notifications, you must first set up Cloud Run functions to process model output and generate events.

Your Cloud Run function connects to the model and listens to its output as its post-processing action. The Cloud Run function you should return an AppPlatformCloudFunctionResponse. The events (appplatformeventbody) are sent to the Pub/Sub topic you configure in the next step.

Sample Cloud Run function (occupancy analytics model)

/**
* Responds to any HTTP request.
*
* @param {!express:Request} req HTTP request context.
* @param {!express:Response} res HTTP response context.
*/
exports.hello_http = (req, res) => {
// Logging statement can be read with cmd `gcloud functions logs read {$functionName}`.
// For more about logging, please see https://cloud.google.com/functions/docs/monitoring

// The processor output will be stored in req.body.
const messageString = constructMessage(req.body);

// Send your message to operator output with res HTTP response context.
res.status(200).send(messageString);
};

function constructMessage(data) {
// Typically, your processor output should contains appPlatformMetadata & it's designed output.
// Here we will use the occupancy analytics model as an example.
const appPlatformMetadata = data.appPlatformMetadata;
const annotations = data.annotations;
const events = [];
for(const annotation of annotations) {
   events.push({
      "event_message": "Event message goes here",
      "payload" : {
         "attr_key_goes_here" : "val_goes_here"
      },
      "event_id" : "event_id_goes_here"
   });
}

// Typically, your cloud function should return a string represent a JSON which has two fields:
// "annotations" must follow the specification of the target model.
// "events" should be of type "AppPlatformEventBody".
const messageJson = {
   "annotations": annotations,
   "events": events,
};
return JSON.stringify(messageJson);
}

Use the following instructions to to send the model output stream to your Cloud Run function:

Enable model event notification with Pub/Sub

After you have set up Cloud Run functions to process model output and generate events, you can set up event notification with Pub/Sub. To read messages from a topic, you also need to Choose and create a Pub/Sub subscription.

What's next

• Read instructions about how to deploy your app to test model event notification in Deploy and undeploy an application.
• Work through the Vertex AI Vision Occupancy Analytics app with event management codelab.
• Learn more about Pub/Sub and Cloud Run functions in What is Pub/Sub? and the Cloud Run functions overview.