Create a batch prediction job

Creates a batch prediction job using the create_batch_prediction_job method.

Explore further

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

Code sample

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using 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.util.ValueConverter;
import com.google.cloud.aiplatform.v1.AcceleratorType;
import com.google.cloud.aiplatform.v1.BatchDedicatedResources;
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.MachineSpec;
import com.google.cloud.aiplatform.v1.ModelName;
import com.google.protobuf.Value;
import java.io.IOException;

public class CreateBatchPredictionJobSample {

  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 modelName = "MODEL_NAME";
    String instancesFormat = "INSTANCES_FORMAT";
    String gcsSourceUri = "GCS_SOURCE_URI";
    String predictionsFormat = "PREDICTIONS_FORMAT";
    String gcsDestinationOutputUriPrefix = "GCS_DESTINATION_OUTPUT_URI_PREFIX";
    createBatchPredictionJobSample(
        project,
        displayName,
        modelName,
        instancesFormat,
        gcsSourceUri,
        predictionsFormat,
        gcsDestinationOutputUriPrefix);
  }

  static void createBatchPredictionJobSample(
      String project,
      String displayName,
      String model,
      String instancesFormat,
      String gcsSourceUri,
      String predictionsFormat,
      String gcsDestinationOutputUriPrefix)
      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)) {

      // Passing in an empty Value object for model parameters
      Value modelParameters = ValueConverter.EMPTY_VALUE;

      GcsSource gcsSource = GcsSource.newBuilder().addUris(gcsSourceUri).build();
      BatchPredictionJob.InputConfig inputConfig =
          BatchPredictionJob.InputConfig.newBuilder()
              .setInstancesFormat(instancesFormat)
              .setGcsSource(gcsSource)
              .build();
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(gcsDestinationOutputUriPrefix).build();
      BatchPredictionJob.OutputConfig outputConfig =
          BatchPredictionJob.OutputConfig.newBuilder()
              .setPredictionsFormat(predictionsFormat)
              .setGcsDestination(gcsDestination)
              .build();
      MachineSpec machineSpec =
          MachineSpec.newBuilder()
              .setMachineType("n1-standard-2")
              .setAcceleratorType(AcceleratorType.NVIDIA_TESLA_T4)
              .setAcceleratorCount(1)
              .build();
      BatchDedicatedResources dedicatedResources =
          BatchDedicatedResources.newBuilder()
              .setMachineSpec(machineSpec)
              .setStartingReplicaCount(1)
              .setMaxReplicaCount(1)
              .build();
      String modelName = ModelName.of(project, location, model).toString();
      BatchPredictionJob batchPredictionJob =
          BatchPredictionJob.newBuilder()
              .setDisplayName(displayName)
              .setModel(modelName)
              .setModelParameters(modelParameters)
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .setDedicatedResources(dedicatedResources)
              .build();
      LocationName parent = LocationName.of(project, location);
      BatchPredictionJob response = client.createBatchPredictionJob(parent, batchPredictionJob);
      System.out.format("response: %s\n", response);
      System.out.format("\tName: %s\n", response.getName());
    }
  }
}

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using 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_batch_prediction_job_sample(
    project: str,
    display_name: str,
    model_name: str,
    instances_format: str,
    gcs_source_uri: str,
    predictions_format: str,
    gcs_destination_output_uri_prefix: 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)
    model_parameters_dict = {}
    model_parameters = json_format.ParseDict(model_parameters_dict, Value())

    batch_prediction_job = {
        "display_name": display_name,
        # Format: 'projects/{project}/locations/{location}/models/{model_id}'
        "model": model_name,
        "model_parameters": model_parameters,
        "input_config": {
            "instances_format": instances_format,
            "gcs_source": {"uris": [gcs_source_uri]},
        },
        "output_config": {
            "predictions_format": predictions_format,
            "gcs_destination": {"output_uri_prefix": gcs_destination_output_uri_prefix},
        },
        "dedicated_resources": {
            "machine_spec": {
                "machine_type": "n1-standard-2",
                "accelerator_type": aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,
                "accelerator_count": 1,
            },
            "starting_replica_count": 1,
            "max_replica_count": 1,
        },
    }
    parent = f"projects/{project}/locations/{location}"
    response = client.create_batch_prediction_job(
        parent=parent, batch_prediction_job=batch_prediction_job
    )
    print("response:", response)

What's next

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