Agrega lógica de procesamiento con funciones de Cloud Run

Con las funciones de Cloud Run, puedes procesar aún más los datos de salida del modelo entrenado personalizado de Vertex AI y los nodos de apps de BigQuery. Puedes usar estas integraciones con nodos de app de las siguientes maneras:

  • Nodo de modelo personalizado de Vertex AI: Usa funciones de Cloud Run para procesar los resultados de la predicción del modelo personalizado original de Vertex AI.
  • Nodo BigQuery: Usa funciones de Cloud Run para generar filas de BigQuery personalizadas con las anotaciones originales.

Todas las funciones de Cloud Run que uses con App Platform deben cumplir con los siguientes requisitos:

Definiciones de API: AppPlatformMetadata, AppPlatformCloudFunctionRequest y AppPlatformCloudFunctionResponse

// Message of essential metadata of App Platform.
// This message is usually attached to a certain model output annotation for
// customer to identify the source of the data.
message AppPlatformMetadata {
  // The application resource name.
  string application = 1;
  // The instance resource id. Instance is the nested resource of application
  // under collection 'instances'.
  string instance_id = 2;
  // The node name of the application graph.
  string node = 3;
  // The referred model resource name of the application node.
  string processor = 4;
}

// For any Cloud Run function based customer processing logic, customer's cloud
// function is expected to receive AppPlatformCloudFunctionRequest as request
// and send back AppPlatformCloudFunctionResponse as response.
// Message of request from AppPlatform to Cloud Run functions.
message AppPlatformCloudFunctionRequest {
  // The metadata of the AppPlatform for customer to identify the source of the
  // payload.
  AppPlatformMetadata app_platform_metadata = 1;
  // A general annotation message that uses struct format to represent different
  // concrete annotation protobufs.
  message StructedInputAnnotation {
    // The ingestion time of the current annotation.
    int64 ingestion_time_micros = 1;
    // The struct format of the actual annotation.
    protobuf.Struct annotation = 2;
  }
  // The actual annotations to be processed by the customized Cloud Run function.
  repeated StructedInputAnnotation annotations = 2;
}

// Message of the response from customer's Cloud Run function to AppPlatform.
message AppPlatformCloudFunctionResponse {
  // A general annotation message that uses struct format to represent different
  // concrete annotation protobufs.
  message StructedOutputAnnotation {
    // The struct format of the actual annotation.
    protobuf.Struct annotation = 1;
  }

  // The modified annotations that is returned back to AppPlatform.
  // If the annotations fields are empty, then those annotations will be dropped
  // by AppPlatform.
  repeated StructedOutputAnnotation annotations = 2;
}

Ejemplo de uso

Usa el siguiente código para postprocesar las anotaciones del modelo entrenado de forma personalizada de Vertex AI y reemplazarlas por un par clave-valor constante.

Python

import functions_framework
from flask import jsonify

@functions_framework.http
def hello_http(request):
   request_json = request.get_json(silent=True)
   request_args = request.args

   if request_json and 'annotations' in request_json:
       annotations = []
       for ele in request_json['annotations']:
           for k, v in ele.items():
               if k == "annotation":
                if "predictions" in v:
                    # Replace the annotation.
                    v["predictions"][0] = {"user": "googler"}
                    annotations.append({"annotation" : v})
   else:
       annotations = 'Failure'
   return jsonify(annotations=annotations)