从文本分类模型获取预测结果

使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。
本页面介绍如何使用 Google Cloud 控制台或 Vertex AI API 从文本分类模型获取在线(实时)预测和批量预测结果。

在线预测与批量预测之间的区别

在线预测是向模型端点发出的同步请求。如果您要发出请求以响应应用输入,或者在其他需要及时推断的情况下,可以使用在线预测。

批量预测是异步请求。您可以直接从模型资源请求批量预测,而无需将模型部署到端点。对于文本数据,如果您不需要获得即时响应并且希望通过一个请求处理累积数据,则可以使用批量预测。

获取在线预测结果

将模型部署到端点

您必须先将模型部署到端点,然后才能使用该模型执行在线预测。部署模型会将物理资源与模型相关联,以便以低延迟方式执行在线预测。

您可以将多个模型部署到一个端点,也可以将一个模型部署到多个端点。如需详细了解部署模型的方法和使用场景,请参阅部署模型简介

请使用以下方法之一部署模型:

Google Cloud 控制台

  1. 在 Google Cloud 控制台的 Vertex AI 部分中,转到模型页面。

    转到“模型”页面

  2. 点击要部署的模型名称以打开其详情页面。

  3. 选择部署和测试标签页。

    如果模型已部署到任何端点,部署模型 (Deploy your model) 部分中会列出这些端点。

  4. 点击部署到端点

  5. 如需将模型部署到新的端点,请选择创建新端点并为新端点提供名称。如需将模型部署到现有端点,请选择 添加到现有端点,然后从下拉列表中选择端点。

    您可以将多个模型添加到一个端点,也可以将一个模型添加到多个端点。了解详情

  6. 如果您将模型部署到已部署有一个或多个模型的现有端点,则必须为要部署的模型和已部署模型更新流量拆分,以使所有百分比的总和为 100%。

  7. 选择 AutoML 文本,然后按如下方式进行配置:

    1. 如果您要将模型部署到新端点,请接受 100 的流量拆分值。否则,请为端点上所有模型调整流量拆分值,使它们的总和为 100。

    2. 为模型点击完成,当所有流量分配百分比均正确无误时,点击继续

      此时会显示将部署模型的区域。这必须是创建模型的区域。

    3. 点击部署,将模型部署到端点。

API

使用 Vertex AI API 部署模型时,请完成以下步骤:

  1. 根据需要创建端点。
  2. 获取端点 ID。
  3. 将模型部署到端点。

创建端点

如果要将模型部署到现有端点,您可以跳过此步骤。

gcloud CLI

以下示例使用 gcloud ai endpoints create 命令

gcloud ai endpoints create \
  --region=LOCATION \
  --display-name=ENDPOINT_NAME

请替换以下内容:

  • LOCATION:您在其中使用 Vertex AI 的区域。
  • ENDPOINT_NAME:端点的显示名。

Google Cloud CLI 工具可能需要几秒钟才能创建端点。

REST

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:您的区域。
  • PROJECT:您的项目 ID。
  • ENDPOINT_NAME:端点的显示名。
  • PROJECT_NUMBER:您的项目编号

HTTP 方法和网址:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/endpoints

请求 JSON 正文:

{
  "display_name": "ENDPOINT_NAME"
}

如需发送您的请求,请展开以下选项之一:

您应该收到类似以下内容的 JSON 响应:

{
  "name": "projects/PROJECT_NUMBER/locations/LOCATION/endpoints/ENDPOINT_ID/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.CreateEndpointOperationMetadata",
    "genericMetadata": {
      "createTime": "2020-11-05T17:45:42.812656Z",
      "updateTime": "2020-11-05T17:45:42.812656Z"
    }
  }
}
您可以轮询操作状态,直到响应包含 "done": true

Java

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Java API 参考文档


import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.aiplatform.v1.CreateEndpointOperationMetadata;
import com.google.cloud.aiplatform.v1.Endpoint;
import com.google.cloud.aiplatform.v1.EndpointServiceClient;
import com.google.cloud.aiplatform.v1.EndpointServiceSettings;
import com.google.cloud.aiplatform.v1.LocationName;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class CreateEndpointSample {

  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 endpointDisplayName = "YOUR_ENDPOINT_DISPLAY_NAME";
    createEndpointSample(project, endpointDisplayName);
  }

  static void createEndpointSample(String project, String endpointDisplayName)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    EndpointServiceSettings endpointServiceSettings =
        EndpointServiceSettings.newBuilder()
            .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";
      LocationName locationName = LocationName.of(project, location);
      Endpoint endpoint = Endpoint.newBuilder().setDisplayName(endpointDisplayName).build();

      OperationFuture<Endpoint, CreateEndpointOperationMetadata> endpointFuture =
          endpointServiceClient.createEndpointAsync(locationName, endpoint);
      System.out.format("Operation name: %s\n", endpointFuture.getInitialFuture().get().getName());
      System.out.println("Waiting for operation to finish...");
      Endpoint endpointResponse = endpointFuture.get(300, TimeUnit.SECONDS);

      System.out.println("Create Endpoint Response");
      System.out.format("Name: %s\n", endpointResponse.getName());
      System.out.format("Display Name: %s\n", endpointResponse.getDisplayName());
      System.out.format("Description: %s\n", endpointResponse.getDescription());
      System.out.format("Labels: %s\n", endpointResponse.getLabelsMap());
      System.out.format("Create Time: %s\n", endpointResponse.getCreateTime());
      System.out.format("Update Time: %s\n", endpointResponse.getUpdateTime());
    }
  }
}

Node.js

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Node.js API 参考文档

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

// const endpointDisplayName = 'YOUR_ENDPOINT_DISPLAY_NAME';
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';

// 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 createEndpoint() {
  // Configure the parent resource
  const parent = `projects/${project}/locations/${location}`;
  const endpoint = {
    displayName: endpointDisplayName,
  };
  const request = {
    parent,
    endpoint,
  };

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

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

  console.log('Create endpoint response');
  console.log(`\tName : ${result.name}`);
  console.log(`\tDisplay name : ${result.displayName}`);
  console.log(`\tDescription : ${result.description}`);
  console.log(`\tLabels : ${JSON.stringify(result.labels)}`);
  console.log(`\tCreate time : ${JSON.stringify(result.createTime)}`);
  console.log(`\tUpdate time : ${JSON.stringify(result.updateTime)}`);
}
createEndpoint();

Python

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Python API 参考文档

def create_endpoint_sample(
    project: str,
    display_name: str,
    location: str,
):
    aiplatform.init(project=project, location=location)

    endpoint = aiplatform.Endpoint.create(
        display_name=display_name,
        project=project,
        location=location,
    )

    print(endpoint.display_name)
    print(endpoint.resource_name)
    return endpoint

检索端点 ID

您需要端点 ID 才能部署模型。

gcloud CLI

以下示例使用 gcloud ai endpoints list 命令

gcloud ai endpoints list \
  --region=LOCATION \
  --filter=display_name=ENDPOINT_NAME

请替换以下内容:

  • LOCATION:您在其中使用 Vertex AI 的区域。
  • ENDPOINT_NAME:端点的显示名。

请注意 ENDPOINT_ID 列中显示的数字。请在以下步骤中使用此 ID。

REST

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:您的区域。
  • PROJECT:您的项目 ID。
  • ENDPOINT_NAME:端点的显示名。
  • PROJECT_NUMBER:您的项目编号

HTTP 方法和网址:

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/endpoints?filter=display_name=ENDPOINT_NAME

如需发送您的请求,请展开以下选项之一:

您应该收到类似以下内容的 JSON 响应:

{
  "endpoints": [
    {
      "name": "projects/PROJECT_NUMBER/locations/us-central1/endpoints/ENDPOINT_ID",
      "displayName": "ENDPOINT_NAME",
      "etag": "AMEw9yPz5pf4PwBHbRWOGh0PcAxUdjbdX2Jm3QO_amguy3DbZGP5Oi_YUKRywIE-BtLx",
      "createTime": "2020-04-17T18:31:11.585169Z",
      "updateTime": "2020-04-17T18:35:08.568959Z"
    }
  ]
}
请记下 ENDPOINT_ID

部署模型

在下面选择您的语言或环境对应的标签页:

gcloud CLI

以下示例使用 gcloud ai endpoints deploy-model 命令

以下示例将 Model 部署到 Endpoint,但没有在多个 DeployedModel 资源之间拆分流量:

在使用下面的命令数据之前,请先进行以下替换:

  • ENDPOINT_ID:端点的 ID。
  • LOCATION:您在其中使用 Vertex AI 的区域。
  • MODEL_ID:要部署的模型的 ID。
  • DEPLOYED_MODEL_NAMEDeployedModel 的名称。您还可以将 Model 的显示名用于 DeployedModel
  • MIN_REPLICA_COUNT:此部署的最小节点数。节点数可根据预测负载增加或减少,不得超过节点数上限,但始终不会低于此数量。
  • MAX_REPLICA_COUNT:此部署的节点数上限。节点数可根据预测负载增加或减少,但始终不会超出此上限。如果您省略 --max-replica-count 标志,则节点数上限将设置为 --min-replica-count 的值。

执行 gcloud ai endpoints deploy-model 命令:

Linux、macOS 或 Cloud Shell

gcloud ai endpoints deploy-model ENDPOINT_ID\
  --region=LOCATION \
  --model=MODEL_ID \
  --display-name=DEPLOYED_MODEL_NAME \
  --traffic-split=0=100

Windows (PowerShell)

gcloud ai endpoints deploy-model ENDPOINT_ID`
  --region=LOCATION `
  --model=MODEL_ID `
  --display-name=DEPLOYED_MODEL_NAME `
  --traffic-split=0=100

Windows (cmd.exe)

gcloud ai endpoints deploy-model ENDPOINT_ID^
  --region=LOCATION ^
  --model=MODEL_ID ^
  --display-name=DEPLOYED_MODEL_NAME ^
  --traffic-split=0=100
 

拆分流量

上述示例中的 --traffic-split=0=100 标志会将 Endpoint 接收的 100% 预测流量发送到新 DeployedModel(使用临时 ID 0 表示)。如果您的 Endpoint 已有其他 DeployedModel 资源,那么您可以在新 DeployedModel 和旧资源之间拆分流量。例如,如需将 20% 的流量发送到新 DeployedModel,将 80% 发送到旧版本,请运行以下命令。

在使用下面的命令数据之前,请先进行以下替换:

  • OLD_DEPLOYED_MODEL_ID:现有 DeployedModel 的 ID。

执行 gcloud ai endpoints deploy-model 命令:

Linux、macOS 或 Cloud Shell

gcloud ai endpoints deploy-model ENDPOINT_ID\
  --region=LOCATION \
  --model=MODEL_ID \
  --display-name=DEPLOYED_MODEL_NAME \
  --min-replica-count=MIN_REPLICA_COUNT \
  --max-replica-count=MAX_REPLICA_COUNT \
  --traffic-split=0=20,OLD_DEPLOYED_MODEL_ID=80

Windows (PowerShell)

gcloud ai endpoints deploy-model ENDPOINT_ID`
  --region=LOCATION `
  --model=MODEL_ID `
  --display-name=DEPLOYED_MODEL_NAME \
  --min-replica-count=MIN_REPLICA_COUNT `
  --max-replica-count=MAX_REPLICA_COUNT `
  --traffic-split=0=20,OLD_DEPLOYED_MODEL_ID=80

Windows (cmd.exe)

gcloud ai endpoints deploy-model ENDPOINT_ID^
  --region=LOCATION ^
  --model=MODEL_ID ^
  --display-name=DEPLOYED_MODEL_NAME \
  --min-replica-count=MIN_REPLICA_COUNT ^
  --max-replica-count=MAX_REPLICA_COUNT ^
  --traffic-split=0=20,OLD_DEPLOYED_MODEL_ID=80
 

REST

部署此模型。

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:您在其中使用 Vertex AI 的区域。
  • PROJECT:您的项目 ID。
  • ENDPOINT_ID:端点的 ID。
  • MODEL_ID:要部署的模型的 ID。
  • DEPLOYED_MODEL_NAMEDeployedModel 的名称。您还可以将 Model 的显示名用于 DeployedModel
  • TRAFFIC_SPLIT_THIS_MODEL:流向此端点的要路由到使用此操作部署的模型的预测流量百分比。默认值为 100。所有流量百分比之和必须为 100。详细了解流量拆分
  • DEPLOYED_MODEL_ID_N:可选。如果将其他模型部署到此端点,您必须更新其流量拆分百分比,以便所有百分比之和等于 100。
  • TRAFFIC_SPLIT_MODEL_N:已部署模型 ID 密钥的流量拆分百分比值。
  • PROJECT_NUMBER:您的项目编号

HTTP 方法和网址:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/endpoints/ENDPOINT_ID:deployModel

请求 JSON 正文:

{
  "deployedModel": {
    "model": "projects/PROJECT/locations/us-central1/models/MODEL_ID",
    "displayName": "DEPLOYED_MODEL_NAME",
    "automaticResources": {
     }
  },
  "trafficSplit": {
    "0": TRAFFIC_SPLIT_THIS_MODEL,
    "DEPLOYED_MODEL_ID_1": TRAFFIC_SPLIT_MODEL_1,
    "DEPLOYED_MODEL_ID_2": TRAFFIC_SPLIT_MODEL_2
  },
}

如需发送您的请求,请展开以下选项之一:

您应该收到类似以下内容的 JSON 响应:

{
  "name": "projects/PROJECT_ID/locations/LOCATION/endpoints/ENDPOINT_ID/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.DeployModelOperationMetadata",
    "genericMetadata": {
      "createTime": "2020-10-19T17:53:16.502088Z",
      "updateTime": "2020-10-19T17:53:16.502088Z"
    }
  }
}

Java

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Java API 参考文档


import com.google.api.gax.longrunning.OperationFuture;
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 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;

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";
    deployModelSample(project, deployedModelDisplayName, endpointId, modelId);
  }

  static void deployModelSample(
      String project, String deployedModelDisplayName, String endpointId, String modelId)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    EndpointServiceSettings endpointServiceSettings =
        EndpointServiceSettings.newBuilder()
            .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

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Node.js API 参考文档

/**
 * 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,
    // AutoML Vision models require `automatic_resources` field
    // Other model types may require `dedicated_resources` field instead
    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

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Python API 参考文档

def deploy_model_with_automatic_resources_sample(
    project,
    location,
    model_name: 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,
    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)

    model.deploy(
        endpoint=endpoint,
        deployed_model_display_name=deployed_model_display_name,
        traffic_percentage=traffic_percentage,
        traffic_split=traffic_split,
        min_replica_count=min_replica_count,
        max_replica_count=max_replica_count,
        metadata=metadata,
        sync=sync,
    )

    model.wait()

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

获取操作状态

某些请求会启动需要一些时间才能完成的长时间运行的操作。这些请求会返回操作名称,您可以使用该名称查看操作状态或取消操作。Vertex AI 提供辅助方法来调用长时间运行的操作。如需了解详情,请参阅使用长时间运行的操作

使用已部署的模型进行在线预测

如需进行在线预测,请向模型提交一个或多个测试项进行分析,模型会返回基于模型目标的结果。如需详细了解预测结果,请参阅解读结果页面。

控制台

使用 Google Cloud 控制台请求在线预测。您的模型必须部署到端点。

  1. 在 Google Cloud 控制台的 Vertex AI 部分中,转到模型页面。

    转到“模型”页面

  2. 从模型列表中,点击要向其请求预测的模型的名称。

  3. 选择部署和测试标签页。

  4. 测试模型部分下,添加测试项以请求预测。

    用于文本目标的 AutoML 模型要求您在文本字段中输入内容,然后点击预测

    如需了解局部特征重要性,请参阅获取说明

    预测完成后,Vertex AI 会在控制台中返回结果。

API

使用 Vertex AI API 来请求在线预测。您的模型必须部署到端点。

gcloud CLI

  1. 创建名为 request.json 且包含以下内容的文件:

    {
      "instances": [{
        "mimeType": "text/plain",
        "content": "CONTENT"
      }]
    }
    

    请替换以下内容:

    • CONTENT:要对其进行预测的文本片段
  2. 运行以下命令:

    gcloud ai endpoints predict ENDPOINT_ID \
      --region=LOCATION \
      --json-request=request.json
    

    请替换以下内容:

    • ENDPOINT_ID:端点的 ID。
    • LOCATION:您在其中使用 Vertex AI 的区域。

REST

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:端点所在的区域。例如 us-central1
  • PROJECT:您的项目 ID
  • ENDPOINT_ID:端点的 ID
  • CONTENT:要对其进行预测的文本片段
  • DEPLOYED_MODEL_ID:用于进行预测的已部署模型的 ID。

HTTP 方法和网址:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/endpoints/ENDPOINT_ID:predict

请求 JSON 正文:

{
  "instances": [{
    "mimeType": "text/plain",
    "content": "CONTENT"
  }]
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/endpoints/ENDPOINT_ID:predict"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/endpoints/ENDPOINT_ID:predict" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应:

{
  "predictions": [
    {
      "ids": [
        "1234567890123456789",
        "2234567890123456789",
        "3234567890123456789"
      ],
      "displayNames": [
        "GreatService",
        "Suggestion",
        "InfoRequest"
      ],
      "confidences": [
        0.8986392080783844,
        0.81984345316886902,
        0.7722353458404541
      ]
    }
  ],
  "deployedModelId": "0123456789012345678"
}

Java

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Java API 参考文档

import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1.EndpointName;
import com.google.cloud.aiplatform.v1.PredictResponse;
import com.google.cloud.aiplatform.v1.PredictionServiceClient;
import com.google.cloud.aiplatform.v1.PredictionServiceSettings;
import com.google.cloud.aiplatform.v1.schema.predict.instance.TextClassificationPredictionInstance;
import com.google.cloud.aiplatform.v1.schema.predict.prediction.ClassificationPredictionResult;
import com.google.protobuf.Value;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class PredictTextClassificationSingleLabelSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "YOUR_PROJECT_ID";
    String content = "YOUR_TEXT_CONTENT";
    String endpointId = "YOUR_ENDPOINT_ID";

    predictTextClassificationSingleLabel(project, content, endpointId);
  }

  static void predictTextClassificationSingleLabel(
      String project, String content, String endpointId) throws IOException {
    PredictionServiceSettings predictionServiceSettings =
        PredictionServiceSettings.newBuilder()
            .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 (PredictionServiceClient predictionServiceClient =
        PredictionServiceClient.create(predictionServiceSettings)) {
      String location = "us-central1";
      EndpointName endpointName = EndpointName.of(project, location, endpointId);

      TextClassificationPredictionInstance predictionInstance =
          TextClassificationPredictionInstance.newBuilder().setContent(content).build();

      List<Value> instances = new ArrayList<>();
      instances.add(ValueConverter.toValue(predictionInstance));

      PredictResponse predictResponse =
          predictionServiceClient.predict(endpointName, instances, ValueConverter.EMPTY_VALUE);
      System.out.println("Predict Text Classification Response");
      System.out.format("\tDeployed Model Id: %s\n", predictResponse.getDeployedModelId());

      System.out.println("Predictions:\n\n");
      for (Value prediction : predictResponse.getPredictionsList()) {

        ClassificationPredictionResult.Builder resultBuilder =
            ClassificationPredictionResult.newBuilder();

        // Display names and confidences values correspond to
        // IDs in the ID list.
        ClassificationPredictionResult result =
            (ClassificationPredictionResult) ValueConverter.fromValue(resultBuilder, prediction);
        int counter = 0;
        for (Long id : result.getIdsList()) {
          System.out.printf("Label ID: %d\n", id);
          System.out.printf("Label: %s\n", result.getDisplayNames(counter));
          System.out.printf("Confidence: %.4f\n", result.getConfidences(counter));
          counter++;
        }
      }
    }
  }
}

Node.js

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Node.js API 参考文档

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

// const text = 'YOUR_PREDICTION_TEXT';
// const endpointId = 'YOUR_ENDPOINT_ID';
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');
const {instance, prediction} =
  aiplatform.protos.google.cloud.aiplatform.v1.schema.predict;

// Imports the Google Cloud Model Service Client library
const {PredictionServiceClient} = aiplatform.v1;

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

// Instantiates a client
const predictionServiceClient = new PredictionServiceClient(clientOptions);

async function predictTextClassification() {
  // Configure the resources
  const endpoint = `projects/${project}/locations/${location}/endpoints/${endpointId}`;

  const predictionInstance =
    new instance.TextClassificationPredictionInstance({
      content: text,
    });
  const instanceValue = predictionInstance.toValue();

  const instances = [instanceValue];
  const request = {
    endpoint,
    instances,
  };

  const [response] = await predictionServiceClient.predict(request);
  console.log('Predict text classification response');
  console.log(`\tDeployed model id : ${response.deployedModelId}\n\n`);

  console.log('Prediction results:');

  for (const predictionResultValue of response.predictions) {
    const predictionResult =
      prediction.ClassificationPredictionResult.fromValue(
        predictionResultValue
      );

    for (const [i, label] of predictionResult.displayNames.entries()) {
      console.log(`\tDisplay name: ${label}`);
      console.log(`\tConfidences: ${predictionResult.confidences[i]}`);
      console.log(`\tIDs: ${predictionResult.ids[i]}\n\n`);
    }
  }
}
predictTextClassification();

Python

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Python API 参考文档

def predict_text_classification_single_label_sample(
    project, location, endpoint, content
):
    aiplatform.init(project=project, location=location)

    endpoint = aiplatform.Endpoint(endpoint)

    response = endpoint.predict(instances=[{"content": content}], parameters={})

    for prediction_ in response.predictions:
        print(prediction_)

进行批量预测

如需发出批量预测请求,请指定输入源和 Vertex AI 存储预测结果所采用的输出格式

输入数据要求

批量请求的输入指定要发送到模型进行预测的内容。对于文本分类模型,您可以使用 JSON 行文件指定用于进行预测的文档列表,然后将 JSON 行文件存储在 Cloud Storage 存储桶中。以下示例显示了输入 JSON 行文件中的一行。

{"content": "gs://sourcebucket/datasets/texts/source_text.txt", "mimeType": "text/plain"}

请求批量预测

对于批量预测请求,您可以使用 Google Cloud Console 或 Vertex AI API。批量预测任务可能需要一些时间才能完成,具体取决于提交的输入数据项数量。

Google Cloud 控制台

使用 Google Cloud 控制台请求批量预测。

  1. 在 Google Cloud 控制台的 Vertex AI 部分中,前往批量预测页面。

    前往“批量预测”页面

  2. 点击创建以打开新建批量预测窗口,完成以下步骤:

    1. 输入批量预测的名称。
    2. 对于模型名称,选择要用于此批量预测的模型的名称。
    3. 对于来源路径,指定 JSON 行输入文件所在的 Cloud Storage 位置。
    4. 对于目标路径,指定存储批量预测结果的 Cloud Storage 位置。输出格式取决于模型的目标。用于文本目标的 AutoML 模型会输出 JSON 行文件。

API

使用 Vertex AI API 发送批量预测请求。

REST

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:存储模型和执行批量预测作业的区域。例如 us-central1
  • PROJECT:您的项目 ID
  • BATCH_JOB_NAME:批处理作业的显示名
  • MODEL_ID:用于执行预测的模型的 ID
  • URI:输入 JSON 行文件所在的 Cloud Storage URI。
  • BUCKET:您的 Cloud Storage 存储桶
  • PROJECT_NUMBER:您的项目编号

HTTP 方法和网址:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/batchPredictionJobs

请求 JSON 正文:

{
    "displayName": "BATCH_JOB_NAME",
    "model": "projects/PROJECT/locations/LOCATION/MODEL_ID",
    "inputConfig": {
        "instancesFormat": "jsonl",
        "gcsSource": {
            "uris": ["URI"],
        },
    },
    "outputConfig": {
        "predictionsFormat": "jsonl",
        "gcsDestination": {
            "outputUriPrefix": "OUTPUT_BUCKET",
        },
    },
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/batchPredictionJobs"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/batchPredictionJobs" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应:

{
  "name": "projects/PROJECT_NUMBER/locations/LOCATION/batchPredictionJobs/BATCH_JOB_ID",
  "displayName": "BATCH_JOB_NAME 202005291958",
  "model": "projects/PROJECT_NUMBER/locations/LOCATION/models/MODEL_ID",
  "inputConfig": {
    "instancesFormat": "jsonl",
    "gcsSource": {
      "uris": [
        "CONTENT"
      ]
    }
  },
  "outputConfig": {
    "predictionsFormat": "jsonl",
    "gcsDestination": {
      "outputUriPrefix": "BUCKET"
    }
  },
  "state": "JOB_STATE_PENDING",
  "createTime": "2020-05-30T02:58:44.341643Z",
  "updateTime": "2020-05-30T02:58:44.341643Z",
  "modelDisplayName": "MODEL_NAME",
  "modelObjective": "MODEL_OBJECTIVE"
}

您可以使用 BATCH_JOB_ID 轮询批量作业的状态,直到作业 stateJOB_STATE_SUCCEEDED

Java

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Java API 参考文档

import com.google.api.gax.rpc.ApiException;
import com.google.cloud.aiplatform.v1.BatchPredictionJob;
import com.google.cloud.aiplatform.v1.GcsDestination;
import com.google.cloud.aiplatform.v1.GcsSource;
import com.google.cloud.aiplatform.v1.JobServiceClient;
import com.google.cloud.aiplatform.v1.JobServiceSettings;
import com.google.cloud.aiplatform.v1.LocationName;
import com.google.cloud.aiplatform.v1.ModelName;
import java.io.IOException;

public class CreateBatchPredictionJobTextClassificationSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "PROJECT";
    String location = "us-central1";
    String displayName = "DISPLAY_NAME";
    String modelId = "MODEL_ID";
    String gcsSourceUri = "GCS_SOURCE_URI";
    String gcsDestinationOutputUriPrefix = "GCS_DESTINATION_OUTPUT_URI_PREFIX";
    createBatchPredictionJobTextClassificationSample(
        project, location, displayName, modelId, gcsSourceUri, gcsDestinationOutputUriPrefix);
  }

  static void createBatchPredictionJobTextClassificationSample(
      String project,
      String location,
      String displayName,
      String modelId,
      String gcsSourceUri,
      String gcsDestinationOutputUriPrefix)
      throws IOException {
    // The AI Platform services require regional API endpoints.
    JobServiceSettings settings =
        JobServiceSettings.newBuilder()
            .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 (JobServiceClient client = JobServiceClient.create(settings)) {
      try {
        String modelName = ModelName.of(project, location, modelId).toString();
        GcsSource gcsSource = GcsSource.newBuilder().addUris(gcsSourceUri).build();
        BatchPredictionJob.InputConfig inputConfig =
            BatchPredictionJob.InputConfig.newBuilder()
                .setInstancesFormat("jsonl")
                .setGcsSource(gcsSource)
                .build();
        GcsDestination gcsDestination =
            GcsDestination.newBuilder().setOutputUriPrefix(gcsDestinationOutputUriPrefix).build();
        BatchPredictionJob.OutputConfig outputConfig =
            BatchPredictionJob.OutputConfig.newBuilder()
                .setPredictionsFormat("jsonl")
                .setGcsDestination(gcsDestination)
                .build();
        BatchPredictionJob batchPredictionJob =
            BatchPredictionJob.newBuilder()
                .setDisplayName(displayName)
                .setModel(modelName)
                .setInputConfig(inputConfig)
                .setOutputConfig(outputConfig)
                .build();
        LocationName parent = LocationName.of(project, location);
        BatchPredictionJob response = client.createBatchPredictionJob(parent, batchPredictionJob);
        System.out.format("response: %s\n", response);
      } catch (ApiException ex) {
        System.out.format("Exception: %s\n", ex.getLocalizedMessage());
      }
    }
  }
}

Node.js

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Node.js API 参考文档

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

// const batchPredictionDisplayName = 'YOUR_BATCH_PREDICTION_DISPLAY_NAME';
// const modelId = 'YOUR_MODEL_ID';
// const gcsSourceUri = 'YOUR_GCS_SOURCE_URI';
// const gcsDestinationOutputUriPrefix = 'YOUR_GCS_DEST_OUTPUT_URI_PREFIX';
//    eg. "gs://<your-gcs-bucket>/destination_path"
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';

// Imports the Google Cloud Job Service Client library
const {JobServiceClient} = require('@google-cloud/aiplatform').v1;

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

// Instantiates a client
const jobServiceClient = new JobServiceClient(clientOptions);

async function createBatchPredictionJobTextClassification() {
  // Configure the parent resource
  const parent = `projects/${project}/locations/${location}`;
  const modelName = `projects/${project}/locations/${location}/models/${modelId}`;

  const inputConfig = {
    instancesFormat: 'jsonl',
    gcsSource: {uris: [gcsSourceUri]},
  };
  const outputConfig = {
    predictionsFormat: 'jsonl',
    gcsDestination: {outputUriPrefix: gcsDestinationOutputUriPrefix},
  };
  const batchPredictionJob = {
    displayName: batchPredictionDisplayName,
    model: modelName,
    inputConfig,
    outputConfig,
  };
  const request = {
    parent,
    batchPredictionJob,
  };

  // Create batch prediction job request
  const [response] = await jobServiceClient.createBatchPredictionJob(request);

  console.log('Create batch prediction job text classification response');
  console.log(`Name : ${response.name}`);
  console.log('Raw response:');
  console.log(JSON.stringify(response, null, 2));
}
createBatchPredictionJobTextClassification();

Python

如需了解如何安装和使用 Vertex AI 客户端库,请参阅 Vertex AI 客户端库。如需了解详情,请参阅 Vertex AI Python API 参考文档

def create_batch_prediction_job_sample(
    project: str,
    location: str,
    model_resource_name: str,
    job_display_name: str,
    gcs_source: Union[str, Sequence[str]],
    gcs_destination: str,
    sync: bool = True,
):
    aiplatform.init(project=project, location=location)

    my_model = aiplatform.Model(model_resource_name)

    batch_prediction_job = my_model.batch_predict(
        job_display_name=job_display_name,
        gcs_source=gcs_source,
        gcs_destination_prefix=gcs_destination,
        sync=sync,
    )

    batch_prediction_job.wait()

    print(batch_prediction_job.display_name)
    print(batch_prediction_job.resource_name)
    print(batch_prediction_job.state)
    return batch_prediction_job

检索批量预测结果

批量预测任务完成后,预测的输出存储在您在请求中指定的 Cloud Storage 存储桶中。

批量预测结果示例

以下示例演示如何从文本分类模型获取批量预测结果。

{
  "instance": {"content": "gs://bucket/text.txt", "mimeType": "text/plain"},
  "predictions": [
    {
      "ids": [
        "1234567890123456789",
        "2234567890123456789",
        "3234567890123456789"
      ],
      "displayNames": [
        "GreatService",
        "Suggestion",
        "InfoRequest"
      ],
      "confidences": [
        0.8986392080783844,
        0.81984345316886902,
        0.7722353458404541
      ]
    }
  ]
}