Adicione lógica de processamento com funções do Cloud Run

Com as funções do Cloud Run, pode processar ainda mais os dados de saída do modelo com preparação personalizada do Vertex AI e dos nós da app do BigQuery. Pode usar estas integrações com nós de apps das seguintes formas:

  • Nó modelo personalizado do Vertex AI: use funções do Cloud Run para pós-processar os resultados da previsão do modelo personalizado do Vertex AI original.
  • Nó do BigQuery: use funções do Cloud Run para gerar linhas do BigQuery personalizadas com as anotações originais.

Todas as funções do Cloud Run que usa com a App Platform têm de cumprir os seguintes requisitos:

Definições de API: AppPlatformMetadata, AppPlatformCloudFunctionRequest, 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;
}

Exemplos de utilização

Use o seguinte código para pós-processar as anotações do modelo com preparação personalizada da Vertex AI e substituir as anotações por um par de chave-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)