Create a data labeling job for active learning

Creates a data labeling job for active learning using the create_data_labeling_job method.

Code sample

Java

To learn how to install and use the client library for Vertex AI, see Vertex AI 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.cloud.aiplatform.v1.ActiveLearningConfig;
import com.google.cloud.aiplatform.v1.DataLabelingJob;
import com.google.cloud.aiplatform.v1.DatasetName;
import com.google.cloud.aiplatform.v1.JobServiceClient;
import com.google.cloud.aiplatform.v1.JobServiceSettings;
import com.google.cloud.aiplatform.v1.LocationName;
import com.google.gson.JsonArray;
import com.google.gson.JsonObject;
import com.google.protobuf.Value;
import com.google.protobuf.util.JsonFormat;
import java.io.IOException;

public class CreateDataLabelingJobActiveLearningSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "PROJECT";
    String displayName = "DISPLAY_NAME";
    String dataset = "DATASET";
    String instructionUri = "INSTRUCTION_URI";
    String inputsSchemaUri = "INPUTS_SCHEMA_URI";
    String annotationSpec = "ANNOTATION_SPEC";
    createDataLabelingJobActiveLearningSample(
        project, displayName, dataset, instructionUri, inputsSchemaUri, annotationSpec);
  }

  static void createDataLabelingJobActiveLearningSample(
      String project,
      String displayName,
      String dataset,
      String instructionUri,
      String inputsSchemaUri,
      String annotationSpec)
      throws IOException {
    JobServiceSettings settings =
        JobServiceSettings.newBuilder()
            .setEndpoint("us-central1-aiplatform.googleapis.com:443")
            .build();
    String location = "us-central1";

    // 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)) {
      JsonArray jsonAnnotationSpecs = new JsonArray();
      jsonAnnotationSpecs.add(annotationSpec);
      JsonObject jsonInputs = new JsonObject();
      jsonInputs.add("annotation_specs", jsonAnnotationSpecs);
      Value.Builder inputsBuilder = Value.newBuilder();
      JsonFormat.parser().merge(jsonInputs.toString(), inputsBuilder);
      Value inputs = inputsBuilder.build();
      ActiveLearningConfig activeLearningConfig =
          ActiveLearningConfig.newBuilder().setMaxDataItemCount(1).build();

      String datasetName = DatasetName.of(project, location, dataset).toString();

      DataLabelingJob dataLabelingJob =
          DataLabelingJob.newBuilder()
              .setDisplayName(displayName)
              .addDatasets(datasetName)
              .setLabelerCount(1)
              .setInstructionUri(instructionUri)
              .setInputsSchemaUri(inputsSchemaUri)
              .setInputs(inputs)
              .putAnnotationLabels(
                  "aiplatform.googleapis.com/annotation_set_name",
                  "data_labeling_job_active_learning")
              .setActiveLearningConfig(activeLearningConfig)
              .build();
      LocationName parent = LocationName.of(project, location);
      DataLabelingJob response = client.createDataLabelingJob(parent, dataLabelingJob);
      System.out.format("response: %s\n", response);
      System.out.format("Name: %s\n", response.getName());
    }
  }
}

Python

To learn how to install and use the client library for Vertex AI, see Vertex AI 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
from google.protobuf import json_format
from google.protobuf.struct_pb2 import Value


def create_data_labeling_job_active_learning_sample(
    project: str,
    display_name: str,
    dataset: str,
    instruction_uri: str,
    inputs_schema_uri: str,
    annotation_spec: str,
    location: str = "us-central1",
    api_endpoint: str = "us-central1-aiplatform.googleapis.com",
):
    # 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.JobServiceClient(client_options=client_options)
    inputs_dict = {"annotation_specs": [annotation_spec]}
    inputs = json_format.ParseDict(inputs_dict, Value())

    active_learning_config = {"max_data_item_count": 1}

    data_labeling_job = {
        "display_name": display_name,
        # Full resource name: projects/{project}/locations/{location}/datasets/{dataset_id}
        "datasets": [dataset],
        "labeler_count": 1,
        "instruction_uri": instruction_uri,
        "inputs_schema_uri": inputs_schema_uri,
        "inputs": inputs,
        "annotation_labels": {
            "aiplatform.googleapis.com/annotation_set_name": "data_labeling_job_active_learning"
        },
        "active_learning_config": active_learning_config,
    }
    parent = f"projects/{project}/locations/{location}"
    response = client.create_data_labeling_job(
        parent=parent, data_labeling_job=data_labeling_job
    )
    print("response:", response)

What's next

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