Deploy a model

Deploys a model using the deploy_model method.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Java API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


import com.google.api.gax.longrunning.OperationFuture;
import com.google.api.gax.longrunning.OperationTimedPollAlgorithm;
import com.google.api.gax.retrying.RetrySettings;
import com.google.cloud.aiplatform.v1.AutomaticResources;
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 com.google.cloud.aiplatform.v1.stub.EndpointServiceStubSettings;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import org.threeten.bp.Duration;

public class DeployModelSample {

  public static void main(String[] args)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "YOUR_PROJECT_ID";
    String deployedModelDisplayName = "YOUR_DEPLOYED_MODEL_DISPLAY_NAME";
    String endpointId = "YOUR_ENDPOINT_NAME";
    String modelId = "YOUR_MODEL_ID";
    int timeout = 900;
    deployModelSample(project, deployedModelDisplayName, endpointId, modelId, timeout);
  }

  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());
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Node.js API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 * (Not necessary if passing values as arguments)
 */

// const modelId = "YOUR_MODEL_ID";
// const endpointId = 'YOUR_ENDPOINT_ID';
// const deployedModelDisplayName = 'YOUR_DEPLOYED_MODEL_DISPLAY_NAME';
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';

const modelName = `projects/${project}/locations/${location}/models/${modelId}`;
const endpoint = `projects/${project}/locations/${location}/endpoints/${endpointId}`;
// Imports the Google Cloud Endpoint Service Client library
const {EndpointServiceClient} = require('@google-cloud/aiplatform');

// Specifies the location of the api endpoint:
const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};

// Instantiates a client
const endpointServiceClient = new EndpointServiceClient(clientOptions);

async function deployModel() {
  // Configure the parent resource
  // 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
  const trafficSplit = {0: 100};
  const deployedModel = {
    // format: 'projects/{project}/locations/{location}/models/{model}'
    model: modelName,
    displayName: deployedModelDisplayName,
    automaticResources: {minReplicaCount: 1, maxReplicaCount: 1},
  };
  const request = {
    endpoint,
    deployedModel,
    trafficSplit,
  };

  // Get and print out a list of all the endpoints for this resource
  const [response] = await endpointServiceClient.deployModel(request);
  console.log(`Long running operation : ${response.name}`);

  // Wait for operation to complete
  await response.promise();
  const result = response.result;

  console.log('Deploy model response');
  const modelDeployed = result.deployedModel;
  console.log('\tDeployed model');
  if (!modelDeployed) {
    console.log('\t\tId : {}');
    console.log('\t\tModel : {}');
    console.log('\t\tDisplay name : {}');
    console.log('\t\tCreate time : {}');

    console.log('\t\tDedicated resources');
    console.log('\t\t\tMin replica count : {}');
    console.log('\t\t\tMachine spec {}');
    console.log('\t\t\t\tMachine type : {}');
    console.log('\t\t\t\tAccelerator type : {}');
    console.log('\t\t\t\tAccelerator count : {}');

    console.log('\t\tAutomatic resources');
    console.log('\t\t\tMin replica count : {}');
    console.log('\t\t\tMax replica count : {}');
  } else {
    console.log(`\t\tId : ${modelDeployed.id}`);
    console.log(`\t\tModel : ${modelDeployed.model}`);
    console.log(`\t\tDisplay name : ${modelDeployed.displayName}`);
    console.log(`\t\tCreate time : ${modelDeployed.createTime}`);

    const dedicatedResources = modelDeployed.dedicatedResources;
    console.log('\t\tDedicated resources');
    if (!dedicatedResources) {
      console.log('\t\t\tMin replica count : {}');
      console.log('\t\t\tMachine spec {}');
      console.log('\t\t\t\tMachine type : {}');
      console.log('\t\t\t\tAccelerator type : {}');
      console.log('\t\t\t\tAccelerator count : {}');
    } else {
      console.log(
        `\t\t\tMin replica count : \
          ${dedicatedResources.minReplicaCount}`
      );
      const machineSpec = dedicatedResources.machineSpec;
      console.log('\t\t\tMachine spec');
      console.log(`\t\t\t\tMachine type : ${machineSpec.machineType}`);
      console.log(
        `\t\t\t\tAccelerator type : ${machineSpec.acceleratorType}`
      );
      console.log(
        `\t\t\t\tAccelerator count : ${machineSpec.acceleratorCount}`
      );
    }

    const automaticResources = modelDeployed.automaticResources;
    console.log('\t\tAutomatic resources');
    if (!automaticResources) {
      console.log('\t\t\tMin replica count : {}');
      console.log('\t\t\tMax replica count : {}');
    } else {
      console.log(
        `\t\t\tMin replica count : \
          ${automaticResources.minReplicaCount}`
      );
      console.log(
        `\t\t\tMax replica count : \
          ${automaticResources.maxReplicaCount}`
      );
    }
  }
}
deployModel();

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

from google.cloud import aiplatform


def deploy_model_sample(
    project: str,
    endpoint_id: str,
    model_name: str,
    deployed_model_display_name: str,
    location: str = "us-central1",
    api_endpoint: str = "us-central1-aiplatform.googleapis.com",
    timeout: int = 7200,
):
    # The AI Platform services require regional API endpoints.
    client_options = {"api_endpoint": api_endpoint}
    # Initialize client that will be used to create and send requests.
    # This client only needs to be created once, and can be reused for multiple requests.
    client = aiplatform.gapic.EndpointServiceClient(client_options=client_options)
    deployed_model = {
        # format: 'projects/{project}/locations/{location}/models/{model}'
        "model": model_name,
        "display_name": deployed_model_display_name,
        # AutoML Vision models require `automatic_resources` field
        # Other model types may require `dedicated_resources` field instead
        "automatic_resources": {"min_replica_count": 1, "max_replica_count": 1},
    }
    # 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
    traffic_split = {"0": 100}
    endpoint = client.endpoint_path(
        project=project, location=location, endpoint=endpoint_id
    )
    response = client.deploy_model(
        endpoint=endpoint, deployed_model=deployed_model, traffic_split=traffic_split
    )
    print("Long running operation:", response.operation.name)
    deploy_model_response = response.result(timeout=timeout)
    print("deploy_model_response:", deploy_model_response)

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.