训练文本实体提取模型

从 2024 年 9 月 15 日起，您只能通过转换到 Vertex AI Gemini 提示和调优来自定义分类、实体提取和情感分析目标。您将无法再针对文本分类、实体提取和情感分析目标训练或更新 Vertex AI AutoML 模型。您可以继续使用现有的 Vertex AI AutoML Text 模型，直到 2025 年 6 月 15 日。如需了解 AutoML 文本和 Gemini 的比较情况，请参阅适用于 AutoML 文本用户的 Gemini。如需详细了解 Gemini 如何通过改进提示功能来提供增强的用户体验，请参阅调优简介。如需开始使用调优，请参阅 Gemini 文本模型的模型调优

本页面介绍了如何使用 Google Cloud 控制台或 Vertex AI API 根据文本数据集训练 AutoML 实体提取模型。

准备工作

在训练文本实体提取模型之前，您必须完成以下操作：

• 准备训练数据
• 创建 Vertex AI 数据集

训练 AutoML 模型

Google Cloud 控制台

1. 在 Google Cloud 控制台的 Vertex AI 部分中，前往数据集页面。

   转到“数据集”页面

2. 点击要用于训练模型的数据集的名称，以打开其详情页面。

3. 选择要用于此模型的注释集。

4. 点击训练新模型。

5. 训练方法选择 AutoML。

6. 点击继续。

7. 输入模型的名称。

8. 如果您要手动设置训练数据的拆分方式，请展开高级选项，然后选择数据拆分选项。了解详情。

9. 点击开始训练。

   模型训练可能需要几个小时，具体取决于数据的大小和复杂性，以及训练预算（如果指定）。您可以关闭此标签页，稍后再返回。模型完成训练后，您会收到电子邮件。

API

选择语言或环境标签页：

REST

创建一个 TrainingPipeline 对象来训练模型。

在使用任何请求数据之前，请先进行以下替换：

• LOCATION：将在其中创建模型的区域，例如 us-central1
• PROJECT：您的项目 ID
• MODEL_DISPLAY_NAME：在界面中显示的模型名称
• DATASET_ID：数据集的 ID
• PROJECT_NUMBER：自动生成的项目编号

HTTP 方法和网址：

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

请求 JSON 正文：

{
  "displayName": "MODEL_DISPLAY_NAME",
  "trainingTaskDefinition": "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_text_extraction_1.0.0.yaml",
  "modelToUpload": {
    "displayName": "MODEL_DISPLAY_NAME"
  },
  "inputDataConfig": {
    "datasetId": "DATASET_ID"
  }
}

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI，或者使用了 Cloud Shell，这会使您自动登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

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/trainingPipelines"

PowerShell (Windows)

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI。您可以运行 gcloud auth list 来检查当前活跃的账号。

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/trainingPipelines" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_NUMBER/locations/us-central1/trainingPipelines/PIPELINE_ID",
  "displayName": "MODEL_DISPLAY_NAME",
  "inputDataConfig": {
    "datasetId": "DATASET_ID"
  },
  "trainingTaskDefinition": "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_text_extraction_1.0.0.yaml",
  "modelToUpload": {
    "displayName": "MODEL_DISPLAY_NAME"
  },
  "state": "PIPELINE_STATE_PENDING",
  "createTime": "2020-04-18T01:22:57.479336Z",
  "updateTime": "2020-04-18T01:22:57.479336Z"
}

Java

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Java 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Java API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1.DeployedModelRef;
import com.google.cloud.aiplatform.v1.EnvVar;
import com.google.cloud.aiplatform.v1.FilterSplit;
import com.google.cloud.aiplatform.v1.FractionSplit;
import com.google.cloud.aiplatform.v1.InputDataConfig;
import com.google.cloud.aiplatform.v1.LocationName;
import com.google.cloud.aiplatform.v1.Model;
import com.google.cloud.aiplatform.v1.Model.ExportFormat;
import com.google.cloud.aiplatform.v1.ModelContainerSpec;
import com.google.cloud.aiplatform.v1.PipelineServiceClient;
import com.google.cloud.aiplatform.v1.PipelineServiceSettings;
import com.google.cloud.aiplatform.v1.Port;
import com.google.cloud.aiplatform.v1.PredefinedSplit;
import com.google.cloud.aiplatform.v1.PredictSchemata;
import com.google.cloud.aiplatform.v1.TimestampSplit;
import com.google.cloud.aiplatform.v1.TrainingPipeline;
import com.google.rpc.Status;
import java.io.IOException;

public class CreateTrainingPipelineTextEntityExtractionSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String trainingPipelineDisplayName = "YOUR_TRAINING_PIPELINE_DISPLAY_NAME";
    String project = "YOUR_PROJECT_ID";
    String datasetId = "YOUR_DATASET_ID";
    String modelDisplayName = "YOUR_MODEL_DISPLAY_NAME";

    createTrainingPipelineTextEntityExtractionSample(
        project, trainingPipelineDisplayName, datasetId, modelDisplayName);
  }

  static void createTrainingPipelineTextEntityExtractionSample(
      String project, String trainingPipelineDisplayName, String datasetId, String modelDisplayName)
      throws IOException {
    PipelineServiceSettings pipelineServiceSettings =
        PipelineServiceSettings.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 (PipelineServiceClient pipelineServiceClient =
        PipelineServiceClient.create(pipelineServiceSettings)) {
      String location = "us-central1";
      String trainingTaskDefinition =
          "gs://google-cloud-aiplatform/schema/trainingjob/definition/"
              + "automl_text_extraction_1.0.0.yaml";

      LocationName locationName = LocationName.of(project, location);

      InputDataConfig trainingInputDataConfig =
          InputDataConfig.newBuilder().setDatasetId(datasetId).build();
      Model model = Model.newBuilder().setDisplayName(modelDisplayName).build();
      TrainingPipeline trainingPipeline =
          TrainingPipeline.newBuilder()
              .setDisplayName(trainingPipelineDisplayName)
              .setTrainingTaskDefinition(trainingTaskDefinition)
              .setTrainingTaskInputs(ValueConverter.EMPTY_VALUE)
              .setInputDataConfig(trainingInputDataConfig)
              .setModelToUpload(model)
              .build();

      TrainingPipeline trainingPipelineResponse =
          pipelineServiceClient.createTrainingPipeline(locationName, trainingPipeline);

      System.out.println("Create Training Pipeline Text Entity Extraction Response");
      System.out.format("\tName: %s\n", trainingPipelineResponse.getName());
      System.out.format("\tDisplay Name: %s\n", trainingPipelineResponse.getDisplayName());

      System.out.format(
          "\tTraining Task Definition %s\n", trainingPipelineResponse.getTrainingTaskDefinition());
      System.out.format(
          "\tTraining Task Inputs: %s\n", trainingPipelineResponse.getTrainingTaskInputs());
      System.out.format(
          "\tTraining Task Metadata: %s\n", trainingPipelineResponse.getTrainingTaskMetadata());
      System.out.format("State: %s\n", trainingPipelineResponse.getState());

      System.out.format("\tCreate Time: %s\n", trainingPipelineResponse.getCreateTime());
      System.out.format("\tStartTime %s\n", trainingPipelineResponse.getStartTime());
      System.out.format("\tEnd Time: %s\n", trainingPipelineResponse.getEndTime());
      System.out.format("\tUpdate Time: %s\n", trainingPipelineResponse.getUpdateTime());
      System.out.format("\tLabels: %s\n", trainingPipelineResponse.getLabelsMap());

      InputDataConfig inputDataConfig = trainingPipelineResponse.getInputDataConfig();
      System.out.println("\tInput Data Config");
      System.out.format("\t\tDataset Id: %s", inputDataConfig.getDatasetId());
      System.out.format("\t\tAnnotations Filter: %s\n", inputDataConfig.getAnnotationsFilter());

      FractionSplit fractionSplit = inputDataConfig.getFractionSplit();
      System.out.println("\t\tFraction Split");
      System.out.format("\t\t\tTraining Fraction: %s\n", fractionSplit.getTrainingFraction());
      System.out.format("\t\t\tValidation Fraction: %s\n", fractionSplit.getValidationFraction());
      System.out.format("\t\t\tTest Fraction: %s\n", fractionSplit.getTestFraction());

      FilterSplit filterSplit = inputDataConfig.getFilterSplit();
      System.out.println("\t\tFilter Split");
      System.out.format("\t\t\tTraining Filter: %s\n", filterSplit.getTrainingFilter());
      System.out.format("\t\t\tValidation Filter: %s\n", filterSplit.getValidationFilter());
      System.out.format("\t\t\tTest Filter: %s\n", filterSplit.getTestFilter());

      PredefinedSplit predefinedSplit = inputDataConfig.getPredefinedSplit();
      System.out.println("\t\tPredefined Split");
      System.out.format("\t\t\tKey: %s\n", predefinedSplit.getKey());

      TimestampSplit timestampSplit = inputDataConfig.getTimestampSplit();
      System.out.println("\t\tTimestamp Split");
      System.out.format("\t\t\tTraining Fraction: %s\n", timestampSplit.getTrainingFraction());
      System.out.format("\t\t\tValidation Fraction: %s\n", timestampSplit.getValidationFraction());
      System.out.format("\t\t\tTest Fraction: %s\n", timestampSplit.getTestFraction());
      System.out.format("\t\t\tKey: %s\n", timestampSplit.getKey());

      Model modelResponse = trainingPipelineResponse.getModelToUpload();
      System.out.println("\tModel To Upload");
      System.out.format("\t\tName: %s\n", modelResponse.getName());
      System.out.format("\t\tDisplay Name: %s\n", modelResponse.getDisplayName());
      System.out.format("\t\tDescription: %s\n", modelResponse.getDescription());

      System.out.format("\t\tMetadata Schema Uri: %s\n", modelResponse.getMetadataSchemaUri());
      System.out.format("\t\tMetadata: %s\n", modelResponse.getMetadata());
      System.out.format("\t\tTraining Pipeline: %s\n", modelResponse.getTrainingPipeline());
      System.out.format("\t\tArtifact Uri: %s\n", modelResponse.getArtifactUri());

      System.out.format(
          "\t\tSupported Deployment Resources Types: %s\n",
          modelResponse.getSupportedDeploymentResourcesTypesList());
      System.out.format(
          "\t\tSupported Input Storage Formats: %s\n",
          modelResponse.getSupportedInputStorageFormatsList());
      System.out.format(
          "\t\tSupported Output Storage Formats: %s\n",
          modelResponse.getSupportedOutputStorageFormatsList());

      System.out.format("\t\tCreate Time: %s\n", modelResponse.getCreateTime());
      System.out.format("\t\tUpdate Time: %s\n", modelResponse.getUpdateTime());
      System.out.format("\t\tLabels: %sn\n", modelResponse.getLabelsMap());

      PredictSchemata predictSchemata = modelResponse.getPredictSchemata();
      System.out.println("\t\tPredict Schemata");
      System.out.format("\t\t\tInstance Schema Uri: %s\n", predictSchemata.getInstanceSchemaUri());
      System.out.format(
          "\t\t\tParameters Schema Uri: %s\n", predictSchemata.getParametersSchemaUri());
      System.out.format(
          "\t\t\tPrediction Schema Uri: %s\n", predictSchemata.getPredictionSchemaUri());

      for (ExportFormat exportFormat : modelResponse.getSupportedExportFormatsList()) {
        System.out.println("\t\tSupported Export Format");
        System.out.format("\t\t\tId: %s\n", exportFormat.getId());
      }

      ModelContainerSpec modelContainerSpec = modelResponse.getContainerSpec();
      System.out.println("\t\tContainer Spec");
      System.out.format("\t\t\tImage Uri: %s\n", modelContainerSpec.getImageUri());
      System.out.format("\t\t\tCommand: %s\n", modelContainerSpec.getCommandList());
      System.out.format("\t\t\tArgs: %s\n", modelContainerSpec.getArgsList());
      System.out.format("\t\t\tPredict Route: %s\n", modelContainerSpec.getPredictRoute());
      System.out.format("\t\t\tHealth Route: %s\n", modelContainerSpec.getHealthRoute());

      for (EnvVar envVar : modelContainerSpec.getEnvList()) {
        System.out.println("\t\t\tEnv");
        System.out.format("\t\t\t\tName: %s\n", envVar.getName());
        System.out.format("\t\t\t\tValue: %s\n", envVar.getValue());
      }

      for (Port port : modelContainerSpec.getPortsList()) {
        System.out.println("\t\t\tPort");
        System.out.format("\t\t\t\tContainer Port: %s\n", port.getContainerPort());
      }

      for (DeployedModelRef deployedModelRef : modelResponse.getDeployedModelsList()) {
        System.out.println("\t\tDeployed Model");
        System.out.format("\t\t\tEndpoint: %s\n", deployedModelRef.getEndpoint());
        System.out.format("\t\t\tDeployed Model Id: %s\n", deployedModelRef.getDeployedModelId());
      }

      Status status = trainingPipelineResponse.getError();
      System.out.println("\tError");
      System.out.format("\t\tCode: %s\n", status.getCode());
      System.out.format("\t\tMessage: %s\n", status.getMessage());
    }
  }
}

Node.js

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Node.js 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Node.js API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

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

// const datasetId = 'YOUR_DATASET_ID';
// const modelDisplayName = 'YOUR_MODEL_DISPLAY_NAME';
// const trainingPipelineDisplayName = 'YOUR_TRAINING_PIPELINE_DISPLAY_NAME';
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');
const {definition} =
  aiplatform.protos.google.cloud.aiplatform.v1.schema.trainingjob;

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

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

// Instantiates a client
const pipelineServiceClient = new PipelineServiceClient(clientOptions);

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

  const trainingTaskInputObj = new definition.AutoMlTextExtractionInputs({});
  const trainingTaskInputs = trainingTaskInputObj.toValue();

  const modelToUpload = {displayName: modelDisplayName};
  const inputDataConfig = {datasetId: datasetId};
  const trainingPipeline = {
    displayName: trainingPipelineDisplayName,
    trainingTaskDefinition:
      'gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_text_extraction_1.0.0.yaml',
    trainingTaskInputs,
    inputDataConfig,
    modelToUpload,
  };
  const request = {
    parent,
    trainingPipeline,
  };

  // Create training pipeline request
  const [response] =
    await pipelineServiceClient.createTrainingPipeline(request);

  console.log('Create training pipeline text entity extraction response :');
  console.log(`Name : ${response.name}`);
  console.log('Raw response:');
  console.log(JSON.stringify(response, null, 2));
}
createTrainingPipelineTextEntityExtraction();

Python

如需了解如何安装或更新 Vertex AI SDK for Python，请参阅安装 Vertex AI SDK for Python。 如需了解详情，请参阅 Python API 参考文档。

def create_training_pipeline_text_entity_extraction_sample(
    project: str,
    location: str,
    display_name: str,
    dataset_id: str,
    model_display_name: Optional[str] = None,
    training_fraction_split: float = 0.8,
    validation_fraction_split: float = 0.1,
    test_fraction_split: float = 0.1,
    budget_milli_node_hours: int = 8000,
    disable_early_stopping: bool = False,
    sync: bool = True,
):
    aiplatform.init(project=project, location=location)

    job = aiplatform.AutoMLTextTrainingJob(
        display_name=display_name, prediction_type="extraction"
    )

    text_dataset = aiplatform.TextDataset(dataset_id)

    model = job.run(
        dataset=text_dataset,
        model_display_name=model_display_name,
        training_fraction_split=training_fraction_split,
        validation_fraction_split=validation_fraction_split,
        test_fraction_split=test_fraction_split,
        budget_milli_node_hours=budget_milli_node_hours,
        disable_early_stopping=disable_early_stopping,
        sync=sync,
    )

    model.wait()

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

使用 REST 控制数据拆分

您可以控制在训练集、验证集和测试集之间拆分训练数据的方式。使用 Vertex AI API 时，请使用 Split 对象来确定数据拆分。Split 对象可以包含在 InputConfig 对象中作为多种对象类型中的一种，其中每种类型都提供一种不同的训练数据拆分方式。您只能选择一种方法。

• FractionSplit:
  • TRAINING_FRACTION：要用于训练集的训练数据的比例。
  • VALIDATION_FRACTION：要用于验证集的训练数据的比例。不用于视频数据。
  • TEST_FRACTION：要用于测试集的训练数据的比例。

  如果指定了任一比例，则必须指定所有比例。这些比例之和必须等于 1.0。比例的默认值会因数据类型而异。了解详情。

  "fractionSplit": {
    "trainingFraction": TRAINING_FRACTION,
    "validationFraction": VALIDATION_FRACTION,
    "testFraction": TEST_FRACTION
  },
  

• FilterSplit：
• TRAINING_FILTER：与此过滤条件匹配的数据项用于训练集。
• VALIDATION_FILTER：与此过滤条件匹配的数据项用于验证集。对于视频数据，该值必须为“-”。
• TEST_FILTER：与此过滤条件匹配的数据项用于测试集。

这些过滤条件可以与 ml_use 标签或应用于数据的任何标签结合使用。详细了解如何使用 ml-use 标签和其他标签来过滤数据。

以下示例展示了如何将 filterSplit 对象与 ml_use 标签结合使用，其中包含验证集：

"filterSplit": {
"trainingFilter": "labels.aiplatform.googleapis.com/ml_use=training",
"validationFilter": "labels.aiplatform.googleapis.com/ml_use=validation",
"testFilter": "labels.aiplatform.googleapis.com/ml_use=test"
}