使用 gcloud CLI 或 Gemini Enterprise API 部署模型

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.aiplatform.v1.DedicatedResources;
import com.google.cloud.aiplatform.v1.DeployModelOperationMetadata;
import com.google.cloud.aiplatform.v1.DeployModelResponse;
import com.google.cloud.aiplatform.v1.DeployedModel;
import com.google.cloud.aiplatform.v1.EndpointName;
import com.google.cloud.aiplatform.v1.EndpointServiceClient;
import com.google.cloud.aiplatform.v1.EndpointServiceSettings;
import com.google.cloud.aiplatform.v1.MachineSpec;
import com.google.cloud.aiplatform.v1.ModelName;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.concurrent.ExecutionException;

public class DeployModelCustomTrainedModelSample {

  public static void main(String[] args)
      throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "PROJECT";
    String endpointId = "ENDPOINT_ID";
    String modelName = "MODEL_NAME";
    String deployedModelDisplayName = "DEPLOYED_MODEL_DISPLAY_NAME";
    deployModelCustomTrainedModelSample(project, endpointId, modelName, deployedModelDisplayName);
  }

  static void deployModelCustomTrainedModelSample(
      String project, String endpointId, String model, String deployedModelDisplayName)
      throws IOException, ExecutionException, InterruptedException {
    EndpointServiceSettings settings =
        EndpointServiceSettings.newBuilder()
            .setEndpoint("us-central1-aiplatform.googleapis.com:443")
            .build();
    String location = "us-central1";

    // 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 client = EndpointServiceClient.create(settings)) {
      MachineSpec machineSpec = MachineSpec.newBuilder().setMachineType("n1-standard-2").build();
      DedicatedResources dedicatedResources =
          DedicatedResources.newBuilder().setMinReplicaCount(1).setMachineSpec(machineSpec).build();

      String modelName = ModelName.of(project, location, model).toString();
      DeployedModel deployedModel =
          DeployedModel.newBuilder()
              .setModel(modelName)
              .setDisplayName(deployedModelDisplayName)
              // `dedicated_resources` must be used for non-AutoML models
              .setDedicatedResources(dedicatedResources)
              .build();
      // 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);
      EndpointName endpoint = EndpointName.of(project, location, endpointId);
      OperationFuture<DeployModelResponse, DeployModelOperationMetadata> response =
          client.deployModelAsync(endpoint, deployedModel, trafficSplit);

      // You can use OperationFuture.getInitialFuture to get a future representing the initial
      // response to the request, which contains information while the operation is in progress.
      System.out.format("Operation name: %s\n", response.getInitialFuture().get().getName());

      // OperationFuture.get() will block until the operation is finished.
      DeployModelResponse deployModelResponse = response.get();
      System.out.format("deployModelResponse: %s\n", deployModelResponse);
    }
  }
}

def deploy_model_with_dedicated_resources_sample(
    project,
    location,
    model_name: str,
    machine_type: str,
    endpoint: Optional[aiplatform.Endpoint] = None,
    deployed_model_display_name: Optional[str] = None,
    traffic_percentage: Optional[int] = 0,
    traffic_split: Optional[Dict[str, int]] = None,
    min_replica_count: int = 1,
    max_replica_count: int = 1,
    accelerator_type: Optional[str] = None,
    accelerator_count: Optional[int] = None,
    explanation_metadata: Optional[explain.ExplanationMetadata] = None,
    explanation_parameters: Optional[explain.ExplanationParameters] = None,
    metadata: Optional[Sequence[Tuple[str, str]]] = (),
    sync: bool = True,
):
    """
    model_name: A fully-qualified model resource name or model ID.
          Example: "projects/123/locations/us-central1/models/456" or
          "456" when project and location are initialized or passed.
    """

    aiplatform.init(project=project, location=location)

    model = aiplatform.Model(model_name=model_name)

    # The explanation_metadata and explanation_parameters should only be
    # provided for a custom trained model and not an AutoML model.
    model.deploy(
        endpoint=endpoint,
        deployed_model_display_name=deployed_model_display_name,
        traffic_percentage=traffic_percentage,
        traffic_split=traffic_split,
        machine_type=machine_type,
        min_replica_count=min_replica_count,
        max_replica_count=max_replica_count,
        accelerator_type=accelerator_type,
        accelerator_count=accelerator_count,
        explanation_metadata=explanation_metadata,
        explanation_parameters=explanation_parameters,
        metadata=metadata,
        sync=sync,
    )

    model.wait()

    print(model.display_name)
    print(model.resource_name)
    return model