テキスト エンティティ抽出モデルのトレーニング用のデータセットを作成する

resource "google_vertex_ai_dataset" "text_dataset" {
  display_name        = "text-dataset"
  metadata_schema_uri = "gs://google-cloud-aiplatform/schema/dataset/metadata/text_1.0.0.yaml"
  region              = "us-central1"
}

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.aiplatform.v1.CreateDatasetOperationMetadata;
import com.google.cloud.aiplatform.v1.Dataset;
import com.google.cloud.aiplatform.v1.DatasetServiceClient;
import com.google.cloud.aiplatform.v1.DatasetServiceSettings;
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 CreateDatasetTextSample {

  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 datasetDisplayName = "YOUR_DATASET_DISPLAY_NAME";

    createDatasetTextSample(project, datasetDisplayName);
  }

  static void createDatasetTextSample(String project, String datasetDisplayName)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    DatasetServiceSettings datasetServiceSettings =
        DatasetServiceSettings.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 (DatasetServiceClient datasetServiceClient =
        DatasetServiceClient.create(datasetServiceSettings)) {
      String location = "us-central1";
      String metadataSchemaUri =
          "gs://google-cloud-aiplatform/schema/dataset/metadata/text_1.0.0.yaml";

      LocationName locationName = LocationName.of(project, location);
      Dataset dataset =
          Dataset.newBuilder()
              .setDisplayName(datasetDisplayName)
              .setMetadataSchemaUri(metadataSchemaUri)
              .build();

      OperationFuture<Dataset, CreateDatasetOperationMetadata> datasetFuture =
          datasetServiceClient.createDatasetAsync(locationName, dataset);
      System.out.format("Operation name: %s\n", datasetFuture.getInitialFuture().get().getName());

      System.out.println("Waiting for operation to finish...");
      Dataset datasetResponse = datasetFuture.get(180, TimeUnit.SECONDS);

      System.out.println("Create Text Dataset Response");
      System.out.format("\tName: %s\n", datasetResponse.getName());
      System.out.format("\tDisplay Name: %s\n", datasetResponse.getDisplayName());
      System.out.format("\tMetadata Schema Uri: %s\n", datasetResponse.getMetadataSchemaUri());
      System.out.format("\tMetadata: %s\n", datasetResponse.getMetadata());
      System.out.format("\tCreate Time: %s\n", datasetResponse.getCreateTime());
      System.out.format("\tUpdate Time: %s\n", datasetResponse.getUpdateTime());
      System.out.format("\tLabels: %s\n", datasetResponse.getLabelsMap());
    }
  }
}

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

// const datasetDisplayName = "YOUR_DATASTE_DISPLAY_NAME";
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';

// Imports the Google Cloud Dataset Service Client library
const {DatasetServiceClient} = require('@google-cloud/aiplatform');

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

// Instantiates a client
const datasetServiceClient = new DatasetServiceClient(clientOptions);

async function createDatasetText() {
  // Configure the parent resource
  const parent = `projects/${project}/locations/${location}`;
  // Configure the dataset resource
  const dataset = {
    displayName: datasetDisplayName,
    metadataSchemaUri:
      'gs://google-cloud-aiplatform/schema/dataset/metadata/text_1.0.0.yaml',
  };
  const request = {
    parent,
    dataset,
  };

  // Create Dataset Request
  const [response] = await datasetServiceClient.createDataset(request);
  console.log(`Long running operation: ${response.name}`);

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

  console.log('Create dataset text response');
  console.log(`Name : ${result.name}`);
  console.log(`Display name : ${result.displayName}`);
  console.log(`Metadata schema uri : ${result.metadataSchemaUri}`);
  console.log(`Metadata : ${JSON.stringify(result.metadata)}`);
  console.log(`Labels : ${JSON.stringify(result.labels)}`);
}
createDatasetText();

def create_and_import_dataset_text_sample(
    project: str,
    location: str,
    display_name: str,
    src_uris: Union[str, List[str]],
    sync: bool = True,
):
    aiplatform.init(project=project, location=location)

    ds = aiplatform.TextDataset.create(
        display_name=display_name,
        gcs_source=src_uris,
        import_schema_uri=aiplatform.schema.dataset.ioformat.text.single_label_classification,
        sync=sync,
    )

    ds.wait()

    print(ds.display_name)
    print(ds.resource_name)
    return ds

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.aiplatform.v1.DatasetName;
import com.google.cloud.aiplatform.v1.DatasetServiceClient;
import com.google.cloud.aiplatform.v1.DatasetServiceSettings;
import com.google.cloud.aiplatform.v1.GcsSource;
import com.google.cloud.aiplatform.v1.ImportDataConfig;
import com.google.cloud.aiplatform.v1.ImportDataOperationMetadata;
import com.google.cloud.aiplatform.v1.ImportDataResponse;
import java.io.IOException;
import java.util.Collections;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class ImportDataTextEntityExtractionSample {

  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 datasetId = "YOUR_DATASET_ID";
    String gcsSourceUri = "gs://YOUR_GCS_SOURCE_BUCKET/path_to_your_text_source/[file.jsonl]";

    importDataTextEntityExtractionSample(project, datasetId, gcsSourceUri);
  }

  static void importDataTextEntityExtractionSample(
      String project, String datasetId, String gcsSourceUri)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    DatasetServiceSettings datasetServiceSettings =
        DatasetServiceSettings.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 (DatasetServiceClient datasetServiceClient =
        DatasetServiceClient.create(datasetServiceSettings)) {
      String location = "us-central1";
      String importSchemaUri =
          "gs://google-cloud-aiplatform/schema/dataset/ioformat/"
              + "text_extraction_io_format_1.0.0.yaml";

      GcsSource.Builder gcsSource = GcsSource.newBuilder();
      gcsSource.addUris(gcsSourceUri);
      DatasetName datasetName = DatasetName.of(project, location, datasetId);

      List<ImportDataConfig> importDataConfigList =
          Collections.singletonList(
              ImportDataConfig.newBuilder()
                  .setGcsSource(gcsSource)
                  .setImportSchemaUri(importSchemaUri)
                  .build());

      OperationFuture<ImportDataResponse, ImportDataOperationMetadata> importDataResponseFuture =
          datasetServiceClient.importDataAsync(datasetName, importDataConfigList);
      System.out.format(
          "Operation name: %s\n", importDataResponseFuture.getInitialFuture().get().getName());

      System.out.println("Waiting for operation to finish...");
      ImportDataResponse importDataResponse = importDataResponseFuture.get(300, TimeUnit.SECONDS);
      System.out.format(
          "Import Data Text Entity Extraction Response: %s\n", importDataResponse.toString());
    }
  }
}

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 */

// const datasetId = "YOUR_DATASET_ID";
// const gcsSourceUri = "YOUR_GCS_SOURCE_URI";
// eg. "gs://<your-gcs-bucket>/<import_source_path>/[file.csv/file.jsonl]"
// const project = "YOUR_PROJECT_ID";
// const location = 'YOUR_PROJECT_LOCATION';

// Imports the Google Cloud Dataset Service Client library
const {DatasetServiceClient} = require('@google-cloud/aiplatform');

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

async function importDataTextEntityExtraction() {
  const name = datasetServiceClient.datasetPath(project, location, datasetId);
  // Here we use only one import config with one source
  const importConfigs = [
    {
      gcsSource: {uris: [gcsSourceUri]},
      importSchemaUri:
        'gs://google-cloud-aiplatform/schema/dataset/ioformat/text_extraction_io_format_1.0.0.yaml',
    },
  ];
  const request = {
    name,
    importConfigs,
  };

  // Import data request
  const [response] = await datasetServiceClient.importData(request);
  console.log(`Long running operation : ${response.name}`);

  // Wait for operation to complete
  const [importDataResponse] = await response.promise();

  console.log(
    `Import data text entity extraction response  : \
      ${JSON.stringify(importDataResponse.result)}`
  );
}
importDataTextEntityExtraction();

def import_data_text_entity_extraction_sample(
    project: str,
    location: str,
    dataset: str,
    src_uris: Union[str, List[str]],
    sync: bool = True,
):
    aiplatform.init(project=project, location=location)

    ds = aiplatform.TextDataset(dataset)
    ds.import_data(
        gcs_source=src_uris,
        import_schema_uri=aiplatform.schema.dataset.ioformat.text.extraction,
        sync=sync,
    )

    ds.wait()

    print(ds.display_name)
    print(ds.resource_name)
    return ds