Create a data label instruction

Creates a data labeling instruction for the given Google Cloud project.

Explore further

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

• Creating instructions for human labelers

Code sample

Java

To learn how to install and use the client library for Data Labeling Service, see Data Labeling Service client libraries. For more information, see the Data Labeling Service Java API reference documentation.

To authenticate to Data Labeling Service, 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.cloud.datalabeling.v1beta1.CreateInstructionMetadata;
import com.google.cloud.datalabeling.v1beta1.CreateInstructionRequest;
import com.google.cloud.datalabeling.v1beta1.DataLabelingServiceClient;
import com.google.cloud.datalabeling.v1beta1.DataLabelingServiceSettings;
import com.google.cloud.datalabeling.v1beta1.DataType;
import com.google.cloud.datalabeling.v1beta1.Instruction;
import com.google.cloud.datalabeling.v1beta1.PdfInstruction;
import com.google.cloud.datalabeling.v1beta1.ProjectName;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class CreateInstruction {

  // Create a instruction for a dataset.
  static void createInstruction(String projectId, String pdfUri) throws IOException {
    // String projectId = "YOUR_PROJECT_ID";
    // String pdfUri = "gs://YOUR_BUCKET_ID/path_to_pdf_or_csv";


    DataLabelingServiceSettings settings =
        DataLabelingServiceSettings.newBuilder()
            .build();
    try (DataLabelingServiceClient dataLabelingServiceClient =
        DataLabelingServiceClient.create(settings)) {
      ProjectName projectName = ProjectName.of(projectId);

      // There are two types of instructions: CSV (CsvInstruction) or PDF (PdfInstruction)
      PdfInstruction pdfInstruction = PdfInstruction.newBuilder().setGcsFileUri(pdfUri).build();

      Instruction instruction =
          Instruction.newBuilder()
              .setDisplayName("YOUR_INSTRUCTION_DISPLAY_NAME")
              .setDescription("YOUR_DESCRIPTION")
              .setDataType(DataType.IMAGE) // DataTypes: AUDIO, IMAGE, VIDEO, TEXT
              .setPdfInstruction(pdfInstruction) // .setCsvInstruction() or .setPdfInstruction()
              .build();

      CreateInstructionRequest createInstructionRequest =
          CreateInstructionRequest.newBuilder()
              .setInstruction(instruction)
              .setParent(projectName.toString())
              .build();

      OperationFuture<Instruction, CreateInstructionMetadata> operation =
          dataLabelingServiceClient.createInstructionAsync(createInstructionRequest);

      Instruction result = operation.get();

      System.out.format("Name: %s\n", result.getName());
      System.out.format("DisplayName: %s\n", result.getDisplayName());
      System.out.format("Description: %s\n", result.getDescription());
      System.out.format("GCS SOURCE URI: %s\n", result.getPdfInstruction().getGcsFileUri());
    } catch (IOException | InterruptedException | ExecutionException e) {
      e.printStackTrace();
    }
  }
}

Python

To learn how to install and use the client library for Data Labeling Service, see Data Labeling Service client libraries. For more information, see the Data Labeling Service Python API reference documentation.

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

def create_instruction(project_id, data_type, instruction_gcs_uri):
    """Creates a data labeling PDF instruction for the given Google Cloud
    project. The PDF file should be uploaded to the project in
    Google Cloud Storage.
    """
    from google.cloud import datalabeling_v1beta1 as datalabeling

    client = datalabeling.DataLabelingServiceClient()

    project_path = f"projects/{project_id}"

    pdf_instruction = datalabeling.PdfInstruction(gcs_file_uri=instruction_gcs_uri)

    instruction = datalabeling.Instruction(
        display_name="YOUR_INSTRUCTION_DISPLAY_NAME",
        description="YOUR_DESCRIPTION",
        data_type=data_type,
        pdf_instruction=pdf_instruction,
    )

    operation = client.create_instruction(
        request={"parent": project_path, "instruction": instruction}
    )

    result = operation.result()

    # The format of the resource name:
    # project_id/{project_id}/instruction/{instruction_id}
    print(f"The instruction resource name: {result.name}")
    print(f"Display name: {result.display_name}")
    print(f"Description: {result.description}")
    print("Create time:")
    print(f"\tseconds: {result.create_time.timestamp_pb().seconds}")
    print(f"\tnanos: {result.create_time.timestamp_pb().nanos}")
    print(f"Data type: {datalabeling.DataType(result.data_type).name}")
    print("Pdf instruction:")
    print(f"\tGcs file uri: {result.pdf_instruction.gcs_file_uri}\n")

    return result

What's next

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