static void deployModelSample()

in aiplatform/src/main/java/aiplatform/DeployModelSample.java [56:142]
72 lines of code
1 McCabe index (conditional complexity)

  static void deployModelSample(
      String project,
      String deployedModelDisplayName,
      String endpointId,
      String modelId,
      int timeout)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {

    // Set long-running operations (LROs) timeout
    final OperationTimedPollAlgorithm operationTimedPollAlgorithm =
        OperationTimedPollAlgorithm.create(
            RetrySettings.newBuilder()
                .setInitialRetryDelay(Duration.ofMillis(5000L))
                .setRetryDelayMultiplier(1.5)
                .setMaxRetryDelay(Duration.ofMillis(45000L))
                .setInitialRpcTimeout(Duration.ZERO)
                .setRpcTimeoutMultiplier(1.0)
                .setMaxRpcTimeout(Duration.ZERO)
                .setTotalTimeout(Duration.ofSeconds(timeout))
                .build());

    EndpointServiceStubSettings.Builder endpointServiceStubSettingsBuilder =
        EndpointServiceStubSettings.newBuilder();
    endpointServiceStubSettingsBuilder
        .deployModelOperationSettings()
        .setPollingAlgorithm(operationTimedPollAlgorithm);
    EndpointServiceStubSettings endpointStubSettings = endpointServiceStubSettingsBuilder.build();
    EndpointServiceSettings endpointServiceSettings =
        EndpointServiceSettings.create(endpointStubSettings);
    endpointServiceSettings =
        endpointServiceSettings.toBuilder()
            .setEndpoint("us-central1-aiplatform.googleapis.com:443")
            .build();

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (EndpointServiceClient endpointServiceClient =
        EndpointServiceClient.create(endpointServiceSettings)) {
      String location = "us-central1";
      EndpointName endpointName = EndpointName.of(project, location, endpointId);
      // key '0' assigns traffic for the newly deployed model
      // Traffic percentage values must add up to 100
      // Leave dictionary empty if endpoint should not accept any traffic
      Map<String, Integer> trafficSplit = new HashMap<>();
      trafficSplit.put("0", 100);
      ModelName modelName = ModelName.of(project, location, modelId);
      AutomaticResources automaticResourcesInput =
          AutomaticResources.newBuilder().setMinReplicaCount(1).setMaxReplicaCount(1).build();
      DeployedModel deployedModelInput =
          DeployedModel.newBuilder()
              .setModel(modelName.toString())
              .setDisplayName(deployedModelDisplayName)
              .setAutomaticResources(automaticResourcesInput)
              .build();

      OperationFuture<DeployModelResponse, DeployModelOperationMetadata> deployModelResponseFuture =
          endpointServiceClient.deployModelAsync(endpointName, deployedModelInput, trafficSplit);
      System.out.format(
          "Operation name: %s\n", deployModelResponseFuture.getInitialFuture().get().getName());
      System.out.println("Waiting for operation to finish...");
      DeployModelResponse deployModelResponse = deployModelResponseFuture.get(20, TimeUnit.MINUTES);

      System.out.println("Deploy Model Response");
      DeployedModel deployedModel = deployModelResponse.getDeployedModel();
      System.out.println("\tDeployed Model");
      System.out.format("\t\tid: %s\n", deployedModel.getId());
      System.out.format("\t\tmodel: %s\n", deployedModel.getModel());
      System.out.format("\t\tDisplay Name: %s\n", deployedModel.getDisplayName());
      System.out.format("\t\tCreate Time: %s\n", deployedModel.getCreateTime());

      DedicatedResources dedicatedResources = deployedModel.getDedicatedResources();
      System.out.println("\t\tDedicated Resources");
      System.out.format("\t\t\tMin Replica Count: %s\n", dedicatedResources.getMinReplicaCount());

      MachineSpec machineSpec = dedicatedResources.getMachineSpec();
      System.out.println("\t\t\tMachine Spec");
      System.out.format("\t\t\t\tMachine Type: %s\n", machineSpec.getMachineType());
      System.out.format("\t\t\t\tAccelerator Type: %s\n", machineSpec.getAcceleratorType());
      System.out.format("\t\t\t\tAccelerator Count: %s\n", machineSpec.getAcceleratorCount());

      AutomaticResources automaticResources = deployedModel.getAutomaticResources();
      System.out.println("\t\tAutomatic Resources");
      System.out.format("\t\t\tMin Replica Count: %s\n", automaticResources.getMinReplicaCount());
      System.out.format("\t\t\tMax Replica Count: %s\n", automaticResources.getMaxReplicaCount());
    }
  }