Generare previsioni batch per Gemini

Le previsioni batch consentono di inviare un numero elevato di prompt multimodali in un'unica richiesta batch.

Per ulteriori informazioni sul flusso di lavoro batch e su come formattare i dati di input, consulta Ottenere previsioni batch per Gemini.

Modelli supportati

Sintassi di esempio

L'esempio seguente mostra come inviare una richiesta API di previsione batch utilizzando il comando curl. Questo esempio è specifico per l'archiviazione BigQuery.

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/batchPredictionJobs \
  -d '{
      "displayName": "...",
      "model": "publishers/google/models/${MODEL_ID}",
      "inputConfig": {
        "instancesFormat": "bigquery",
        "bigquerySource": {
          "inputUri" : "..."
        }
      },
      "outputConfig": {
        "predictionsFormat": "bigquery",
        "bigqueryDestination": {
          "outputUri": "..."
        }
      }
  }'

Parametri

Per informazioni dettagliate sull'implementazione, consulta gli esempi.

Corpo della richiesta

Parametri

displayName

Un nome che scegli per il tuo job.

model

Il modello da utilizzare per la previsione batch.

inputConfig

Il formato dei dati. Per la previsione batch di Gemini, sono supportate le origini di input Cloud Storage e BigQuery.

outputConfig

La configurazione dell'output che determina la posizione dell'output del modello. Sono supportate le posizioni di output di Cloud Storage e BigQuery.

inputConfig

Parametri

instancesFormat

Il formato di input del prompt. Utilizza jsonl per Cloud Storage o bigquery per BigQuery.

gcsSource.uris

L'URI dell'origine di input. Si tratta di una posizione Cloud Storage del file JSONL nel formato gs://bucketname/path/to/file.jsonl.

bigquerySource.inputUri

L'URI dell'origine di input. Si tratta di un URI della tabella BigQuery nel formato bq://project_id.dataset.table. La regione del set di dati BigQuery di input deve corrispondere a quella del job di previsione batch di Vertex AI.

outputConfig

Parametri

predictionsFormat

Il formato di output della previsione. Utilizza bigquery.

gcsDestination.outputUriPrefix

La posizione del bucket e della directory Cloud Storage, nel formato gs://mybucket/path/to/output.

bigqueryDestination.outputUri

L'URI BigQuery della tabella di output di destinazione, nel formato bq://project_id.dataset.table. Se la tabella non esiste già, viene creata automaticamente. La regione del set di dati BigQuery di output deve essere la stessa del job di previsione batch di Vertex AI.

Esempi

Richiedere una risposta batch

Le richieste batch per i modelli multimodali accettano origini di archiviazione Cloud Storage e BigQuery. Per saperne di più, consulta le seguenti risorse:

A seconda del numero di elementi di input inviati, il completamento di un'attività di generazione batch può richiedere un po' di tempo.

REST

Per creare un job di previsione batch, utilizza il metodo projects.locations.batchPredictionJobs.create.

Input Cloud Storage

Prima di utilizzare i dati della richiesta, apporta le seguenti sostituzioni:

  • ENDPOINT_PREFIX: la regione della risorsa modello seguita da -. Ad esempio: us-central1-. Se utilizzi l'endpoint globale, lascia vuoto il campo. Nota:l'endpoint globale non è supportato per l'inferenza batch utilizzando modelli ottimizzati.
  • LOCATION: una regione che supporta i modelli Gemini. Se utilizzi l'endpoint globale, inserisci global.
  • PROJECT_ID: il tuo ID progetto.
  • MODEL_PATH: il nome del modello dell'editore, ad esempio publishers/google/models/gemini-2.5-flash; o il nome dell'endpoint ottimizzato, ad esempio projects/PROJECT_ID/locations/LOCATION/models/MODEL_ID, dove MODEL_ID è l'ID modello del modello ottimizzato.
  • INPUT_URI: la posizione Cloud Storage dell'input di previsione batch JSONL, ad esempio gs://bucketname/path/to/file.jsonl.
  • OUTPUT_FORMAT: Per l'output in un bucket Cloud Storage, specifica jsonl.
  • DESTINATION: per BigQuery, specifica bigqueryDestination. Per Cloud Storage, specifica gcsDestination.
  • OUTPUT_URI_FIELD_NAME: Per BigQuery, specifica outputUri. Per Cloud Storage, specifica outputUriPrefix.
  • OUTPUT_URI: per BigQuery, specifica la posizione della tabella, ad esempio bq://myproject.mydataset.output_result. La regione del set di dati BigQuery di output deve essere la stessa del job di previsione batch di Vertex AI. Per Cloud Storage, specifica la posizione del bucket e della directory, ad esempio gs://mybucket/path/to/output.

Corpo JSON della richiesta: 

{
  "displayName": "my-cloud-storage-batch-prediction-job",
  "model": "MODEL_PATH",
  "inputConfig": {
    "instancesFormat": "jsonl",
    "gcsSource": {
      "uris" : "INPUT_URI"
    }
  },
  "outputConfig": {
    "predictionsFormat": "OUTPUT_FORMAT",
    "DESTINATION": {
      "OUTPUT_URI_FIELD_NAME": "OUTPUT_URI"
    }
  }
}

Per inviare la richiesta, scegli una di queste opzioni:

curl

Salva il corpo della richiesta in un file denominato request.json, ed esegui questo comando: 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://ENDPOINT_PREFIXaiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs"

PowerShell

Salva il corpo della richiesta in un file denominato request.json, ed esegui questo comando: 

$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://ENDPOINT_PREFIXaiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs" | Select-Object -Expand Content

Dovresti ricevere una risposta JSON simile alla seguente.

Input BigQuery

Prima di utilizzare i dati della richiesta, apporta le seguenti sostituzioni:

  • LOCATION: una regione che supporta i modelli Gemini.
  • PROJECT_ID: il tuo ID progetto
  • MODEL_PATH: il nome del modello del publisher, ad esempio publishers/google/models/gemini-2.0-flash-001; o il nome dell'endpoint ottimizzato, ad esempio projects/PROJECT_ID/locations/LOCATION/models/MODEL_ID, dove MODEL_ID è l'ID modello del modello ottimizzato.
  • INPUT_URI: la tabella BigQuery in cui si trova l'input della previsione batch come bq://myproject.mydataset.input_table. Il set di dati deve trovarsi nella stessa regione del job di previsione batch. I set di dati multiregionali non sono supportati.
  • OUTPUT_FORMAT: per l'output in una tabella BigQuery, specifica bigquery. Per l'output in un bucket Cloud Storage, specifica jsonl.
  • DESTINATION: per BigQuery, specifica bigqueryDestination. Per Cloud Storage, specifica gcsDestination.
  • OUTPUT_URI_FIELD_NAME: Per BigQuery, specifica outputUri. Per Cloud Storage, specifica outputUriPrefix.
  • OUTPUT_URI: per BigQuery, specifica la posizione della tabella, ad esempio bq://myproject.mydataset.output_result. La regione del set di dati BigQuery di output deve essere la stessa del job di previsione batch di Vertex AI. Per Cloud Storage, specifica la posizione del bucket e della directory, ad esempio gs://mybucket/path/to/output.

Corpo JSON della richiesta: 

{
  "displayName": "my-bigquery-batch-prediction-job",
  "model": "MODEL_PATH",
  "inputConfig": {
    "instancesFormat": "bigquery",
    "bigquerySource":{
      "inputUri" : "INPUT_URI"
    }
  },
  "outputConfig": {
    "predictionsFormat": "OUTPUT_FORMAT",
    "DESTINATION": {
      "OUTPUT_URI_FIELD_NAME": "OUTPUT_URI"
    }
  }
}

Per inviare la richiesta, scegli una di queste opzioni:

curl

Salva il corpo della richiesta in un file denominato request.json, ed esegui questo comando: 

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_ID/locations/LOCATION/batchPredictionJobs"

PowerShell

Salva il corpo della richiesta in un file denominato request.json, ed esegui questo comando: 

$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_ID/locations/LOCATION/batchPredictionJobs" | Select-Object -Expand Content

Dovresti ricevere una risposta JSON simile alla seguente.
La risposta include un identificatore univoco per il job batch. Puoi eseguire il polling dello stato del job batch utilizzando BATCH_JOB_ID. Per saperne di più, vedi Monitorare lo stato del job. Nota: i report su service account personalizzato, stato di avanzamento in tempo reale, CMEK e VPCSC non sono supportati.

Python

Installa

pip install --upgrade google-genai

Per saperne di più, consulta la documentazione di riferimento dell'SDK.

Imposta le variabili di ambiente per utilizzare l'SDK Gen AI con Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

Input Cloud Storage

import time

from google import genai
from google.genai.types import CreateBatchJobConfig, JobState, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
# TODO(developer): Update and un-comment below line
# output_uri = "gs://your-bucket/your-prefix"

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.batches.Batches.create
job = client.batches.create(
    # To use a tuned model, set the model param to your tuned model using the following format:
    # model="projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}
    model="gemini-2.5-flash",
    # Source link: https://storage.cloud.google.com/cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl
    src="gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl",
    config=CreateBatchJobConfig(dest=output_uri),
)
print(f"Job name: {job.name}")
print(f"Job state: {job.state}")
# Example response:
# Job name: projects/.../locations/.../batchPredictionJobs/9876453210000000000
# Job state: JOB_STATE_PENDING

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.types.BatchJob
completed_states = {
    JobState.JOB_STATE_SUCCEEDED,
    JobState.JOB_STATE_FAILED,
    JobState.JOB_STATE_CANCELLED,
    JobState.JOB_STATE_PAUSED,
}

while job.state not in completed_states:
    time.sleep(30)
    job = client.batches.get(name=job.name)
    print(f"Job state: {job.state}")
# Example response:
# Job state: JOB_STATE_PENDING
# Job state: JOB_STATE_RUNNING
# Job state: JOB_STATE_RUNNING
# ...
# Job state: JOB_STATE_SUCCEEDED

Input BigQuery

import time

from google import genai
from google.genai.types import CreateBatchJobConfig, JobState, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))

# TODO(developer): Update and un-comment below line
# output_uri = f"bq://your-project.your_dataset.your_table"

job = client.batches.create(
    # To use a tuned model, set the model param to your tuned model using the following format:
    # model="projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}
    model="gemini-2.5-flash",
    src="bq://storage-samples.generative_ai.batch_requests_for_multimodal_input",
    config=CreateBatchJobConfig(dest=output_uri),
)
print(f"Job name: {job.name}")
print(f"Job state: {job.state}")
# Example response:
# Job name: projects/.../locations/.../batchPredictionJobs/9876453210000000000
# Job state: JOB_STATE_PENDING

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.types.BatchJob
completed_states = {
    JobState.JOB_STATE_SUCCEEDED,
    JobState.JOB_STATE_FAILED,
    JobState.JOB_STATE_CANCELLED,
    JobState.JOB_STATE_PAUSED,
}

while job.state not in completed_states:
    time.sleep(30)
    job = client.batches.get(name=job.name)
    print(f"Job state: {job.state}")
# Example response:
# Job state: JOB_STATE_PENDING
# Job state: JOB_STATE_RUNNING
# Job state: JOB_STATE_RUNNING
# ...
# Job state: JOB_STATE_SUCCEEDED

Node.js

Prima di provare questo esempio, segui le istruzioni di configurazione di Node.js nella guida rapida di Vertex AI per l'utilizzo delle librerie client. Per saperne di più, consulta la documentazione di riferimento dell'API Vertex AI Node.js.

Per eseguire l'autenticazione in Vertex AI, configura le Credenziali predefinite dell'applicazione. Per ulteriori informazioni, consulta Configura l'autenticazione per un ambiente di sviluppo locale.

Input Cloud Storage

// Import the aiplatform library
const aiplatformLib = require('@google-cloud/aiplatform');
const aiplatform = aiplatformLib.protos.google.cloud.aiplatform.v1;

/**
 * TODO(developer):  Uncomment/update these variables before running the sample.
 */
// projectId = 'YOUR_PROJECT_ID';
// URI of the output folder in Google Cloud Storage.
// E.g. "gs://[BUCKET]/[OUTPUT]"
// outputUri = 'gs://my-bucket';

// URI of the input file in Google Cloud Storage.
// E.g. "gs://[BUCKET]/[DATASET].jsonl"
// Or try:
// "gs://cloud-samples-data/generative-ai/batch/gemini_multimodal_batch_predict.jsonl"
// for a batch prediction that uses audio, video, and an image.
const inputUri =
  'gs://cloud-samples-data/generative-ai/batch/batch_requests_for_multimodal_input.jsonl';
const location = 'us-central1';
const parent = `projects/${projectId}/locations/${location}`;
const modelName = `${parent}/publishers/google/models/gemini-2.0-flash-001`;

// Specify the location of the api endpoint.
const clientOptions = {
  apiEndpoint: `${location}-aiplatform.googleapis.com`,
};

// Instantiate the client.
const jobServiceClient = new aiplatformLib.JobServiceClient(clientOptions);

// Create a Gemini batch prediction job using Google Cloud Storage input and output buckets.
async function create_batch_prediction_gemini_gcs() {
  const gcsSource = new aiplatform.GcsSource({
    uris: [inputUri],
  });

  const inputConfig = new aiplatform.BatchPredictionJob.InputConfig({
    gcsSource: gcsSource,
    instancesFormat: 'jsonl',
  });

  const gcsDestination = new aiplatform.GcsDestination({
    outputUriPrefix: outputUri,
  });

  const outputConfig = new aiplatform.BatchPredictionJob.OutputConfig({
    gcsDestination: gcsDestination,
    predictionsFormat: 'jsonl',
  });

  const batchPredictionJob = new aiplatform.BatchPredictionJob({
    displayName: 'Batch predict with Gemini - GCS',
    model: modelName,
    inputConfig: inputConfig,
    outputConfig: outputConfig,
  });

  const request = {
    parent: parent,
    batchPredictionJob,
  };

  // Create batch prediction job request
  const [response] = await jobServiceClient.createBatchPredictionJob(request);
  console.log('Response name: ', response.name);
  // Example response:
  // Response name: projects/<project>/locations/us-central1/batchPredictionJobs/<job-id>
}

await create_batch_prediction_gemini_gcs();

Input BigQuery

// Import the aiplatform library
const aiplatformLib = require('@google-cloud/aiplatform');
const aiplatform = aiplatformLib.protos.google.cloud.aiplatform.v1;

/**
 * TODO(developer):  Uncomment/update these variables before running the sample.
 */
// projectId = 'YOUR_PROJECT_ID';
// URI of the output BigQuery table.
// E.g. "bq://[PROJECT].[DATASET].[TABLE]"
// outputUri = 'bq://projectid.dataset.table';

// URI of the multimodal input BigQuery table.
// E.g. "bq://[PROJECT].[DATASET].[TABLE]"
const inputUri =
  'bq://storage-samples.generative_ai.batch_requests_for_multimodal_input';
const location = 'us-central1';
const parent = `projects/${projectId}/locations/${location}`;
const modelName = `${parent}/publishers/google/models/gemini-2.0-flash-001`;

// Specify the location of the api endpoint.
const clientOptions = {
  apiEndpoint: `${location}-aiplatform.googleapis.com`,
};

// Instantiate the client.
const jobServiceClient = new aiplatformLib.JobServiceClient(clientOptions);

// Create a Gemini batch prediction job using BigQuery input and output datasets.
async function create_batch_prediction_gemini_bq() {
  const bqSource = new aiplatform.BigQuerySource({
    inputUri: inputUri,
  });

  const inputConfig = new aiplatform.BatchPredictionJob.InputConfig({
    bigquerySource: bqSource,
    instancesFormat: 'bigquery',
  });

  const bqDestination = new aiplatform.BigQueryDestination({
    outputUri: outputUri,
  });

  const outputConfig = new aiplatform.BatchPredictionJob.OutputConfig({
    bigqueryDestination: bqDestination,
    predictionsFormat: 'bigquery',
  });

  const batchPredictionJob = new aiplatform.BatchPredictionJob({
    displayName: 'Batch predict with Gemini - BigQuery',
    model: modelName, // Add model parameters per request in the input BigQuery table.
    inputConfig: inputConfig,
    outputConfig: outputConfig,
  });

  const request = {
    parent: parent,
    batchPredictionJob,
  };

  // Create batch prediction job request
  const [response] = await jobServiceClient.createBatchPredictionJob(request);
  console.log('Response name: ', response.name);
  // Example response:
  // Response name: projects/<project>/locations/us-central1/batchPredictionJobs/<job-id>
}

await create_batch_prediction_gemini_bq();

Java

Prima di provare questo esempio, segui le istruzioni di configurazione di Java nella guida rapida di Vertex AI per l'utilizzo delle librerie client. Per saperne di più, consulta la documentazione di riferimento dell'API Vertex AI Java.

Per eseguire l'autenticazione in Vertex AI, configura le Credenziali predefinite dell'applicazione. Per ulteriori informazioni, consulta Configura l'autenticazione per un ambiente di sviluppo locale.

Input Cloud Storage

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 java.io.IOException;

public class CreateBatchPredictionGeminiJobSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Update these variables before running the sample.
    String project = "PROJECT_ID";
    String gcsDestinationOutputUriPrefix = "gs://MY_BUCKET/";

    createBatchPredictionGeminiJobSample(project, gcsDestinationOutputUriPrefix);
  }

  // Create a batch prediction job using a JSONL input file and output URI, both in Cloud
  // Storage.
  public static BatchPredictionJob createBatchPredictionGeminiJobSample(
      String project, String gcsDestinationOutputUriPrefix) throws IOException {
    String location = "us-central1";
    JobServiceSettings settings =
        JobServiceSettings.newBuilder()
            .setEndpoint(String.format("%s-aiplatform.googleapis.com:443", location))
            .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.
    try (JobServiceClient client = JobServiceClient.create(settings)) {
      GcsSource gcsSource =
          GcsSource.newBuilder()
              .addUris(
                  "gs://cloud-samples-data/generative-ai/batch/"
                      + "batch_requests_for_multimodal_input.jsonl")
              // Or try
              // "gs://cloud-samples-data/generative-ai/batch/gemini_multimodal_batch_predict.jsonl"
              // for a batch prediction that uses audio, video, and an image.
              .build();
      BatchPredictionJob.InputConfig inputConfig =
          BatchPredictionJob.InputConfig.newBuilder()
              .setInstancesFormat("jsonl")
              .setGcsSource(gcsSource)
              .build();
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(gcsDestinationOutputUriPrefix).build();
      BatchPredictionJob.OutputConfig outputConfig =
          BatchPredictionJob.OutputConfig.newBuilder()
              .setPredictionsFormat("jsonl")
              .setGcsDestination(gcsDestination)
              .build();
      String modelName =
          String.format(
              "projects/%s/locations/%s/publishers/google/models/%s",
              project, location, "gemini-2.0-flash-001");

      BatchPredictionJob batchPredictionJob =
          BatchPredictionJob.newBuilder()
              .setDisplayName("my-display-name")
              .setModel(modelName) // Add model parameters per request in the input jsonl file.
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      LocationName parent = LocationName.of(project, location);
      BatchPredictionJob response = client.createBatchPredictionJob(parent, batchPredictionJob);
      System.out.format("\tName: %s\n", response.getName());
      // Example response:
      //   Name: projects/<project>/locations/us-central1/batchPredictionJobs/<job-id>
      return response;
    }
  }
}

Input BigQuery

import com.google.cloud.aiplatform.v1.BatchPredictionJob;
import com.google.cloud.aiplatform.v1.BigQueryDestination;
import com.google.cloud.aiplatform.v1.BigQuerySource;
import com.google.cloud.aiplatform.v1.JobServiceClient;
import com.google.cloud.aiplatform.v1.JobServiceSettings;
import com.google.cloud.aiplatform.v1.LocationName;
import java.io.IOException;

public class CreateBatchPredictionGeminiBigqueryJobSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Update these variables before running the sample.
    String project = "PROJECT_ID";
    String bigqueryDestinationOutputUri = "bq://PROJECT_ID.MY_DATASET.MY_TABLE";

    createBatchPredictionGeminiBigqueryJobSample(project, bigqueryDestinationOutputUri);
  }

  // Create a batch prediction job using BigQuery input and output datasets.
  public static BatchPredictionJob createBatchPredictionGeminiBigqueryJobSample(
      String project, String bigqueryDestinationOutputUri) throws IOException {
    String location = "us-central1";
    JobServiceSettings settings =
        JobServiceSettings.newBuilder()
            .setEndpoint(String.format("%s-aiplatform.googleapis.com:443", location))
            .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.
    try (JobServiceClient client = JobServiceClient.create(settings)) {
      BigQuerySource bigquerySource =
          BigQuerySource.newBuilder()
              .setInputUri("bq://storage-samples.generative_ai.batch_requests_for_multimodal_input")
              .build();
      BatchPredictionJob.InputConfig inputConfig =
          BatchPredictionJob.InputConfig.newBuilder()
              .setInstancesFormat("bigquery")
              .setBigquerySource(bigquerySource)
              .build();
      BigQueryDestination bigqueryDestination =
          BigQueryDestination.newBuilder().setOutputUri(bigqueryDestinationOutputUri).build();
      BatchPredictionJob.OutputConfig outputConfig =
          BatchPredictionJob.OutputConfig.newBuilder()
              .setPredictionsFormat("bigquery")
              .setBigqueryDestination(bigqueryDestination)
              .build();
      String modelName =
          String.format(
              "projects/%s/locations/%s/publishers/google/models/%s",
              project, location, "gemini-2.0-flash-001");

      BatchPredictionJob batchPredictionJob =
          BatchPredictionJob.newBuilder()
              .setDisplayName("my-display-name")
              .setModel(modelName) // Add model parameters per request in the input BigQuery table.
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      LocationName parent = LocationName.of(project, location);
      BatchPredictionJob response = client.createBatchPredictionJob(parent, batchPredictionJob);
      System.out.format("\tName: %s\n", response.getName());
      // Example response:
      //   Name: projects/<project>/locations/us-central1/batchPredictionJobs/<job-id>
      return response;
    }
  }
}

Go

Prima di provare questo esempio, segui le istruzioni di configurazione di Go nella guida rapida di Vertex AI per l'utilizzo delle librerie client. Per saperne di più, consulta la documentazione di riferimento dell'API Vertex AI Go.

Per eseguire l'autenticazione in Vertex AI, configura le Credenziali predefinite dell'applicazione. Per ulteriori informazioni, consulta Configura l'autenticazione per un ambiente di sviluppo locale.

Input Cloud Storage

import (
	"context"
	"fmt"
	"io"
	"time"

	aiplatform "cloud.google.com/go/aiplatform/apiv1"
	aiplatformpb "cloud.google.com/go/aiplatform/apiv1/aiplatformpb"

	"google.golang.org/api/option"
	"google.golang.org/protobuf/types/known/structpb"
)

// batchPredictGCS submits a batch prediction job using GCS data source as its input
func batchPredictGCS(w io.Writer, projectID, location string, inputURIs []string, outputURI string) error {
	// location := "us-central1"
	// inputURIs := []string{"gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl"}
	// outputURI := "gs://<cloud-bucket-name>/<prefix-name>"
	modelName := "gemini-2.0-flash-001"
	jobName := "batch-predict-gcs-test-001"

	ctx := context.Background()
	apiEndpoint := fmt.Sprintf("%s-aiplatform.googleapis.com:443", location)
	client, err := aiplatform.NewJobClient(ctx, option.WithEndpoint(apiEndpoint))
	if err != nil {
		return fmt.Errorf("unable to create aiplatform client: %w", err)
	}
	defer client.Close()

	modelParameters, err := structpb.NewValue(map[string]interface{}{
		"temperature":     0.2,
		"maxOutputTokens": 200,
	})
	if err != nil {
		return fmt.Errorf("unable to convert model parameters to protobuf value: %w", err)
	}

	req := &aiplatformpb.CreateBatchPredictionJobRequest{
		Parent: fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		BatchPredictionJob: &aiplatformpb.BatchPredictionJob{
			DisplayName:     jobName,
			Model:           fmt.Sprintf("publishers/google/models/%s", modelName),
			ModelParameters: modelParameters,
			// Check the API reference for `BatchPredictionJob` for supported input and output formats:
			// https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.BatchPredictionJob
			InputConfig: &aiplatformpb.BatchPredictionJob_InputConfig{
				Source: &aiplatformpb.BatchPredictionJob_InputConfig_GcsSource{
					GcsSource: &aiplatformpb.GcsSource{
						Uris: inputURIs,
					},
				},
				InstancesFormat: "jsonl",
			},
			OutputConfig: &aiplatformpb.BatchPredictionJob_OutputConfig{
				Destination: &aiplatformpb.BatchPredictionJob_OutputConfig_GcsDestination{
					GcsDestination: &aiplatformpb.GcsDestination{
						OutputUriPrefix: outputURI,
					},
				},
				PredictionsFormat: "jsonl",
			},
		},
	}

	job, err := client.CreateBatchPredictionJob(ctx, req)
	if err != nil {
		return err
	}
	fullJobId := job.GetName()
	fmt.Fprintf(w, "submitted batch predict job for model %q\n", job.GetModel())
	fmt.Fprintf(w, "job id: %q\n", fullJobId)
	fmt.Fprintf(w, "job state: %s\n", job.GetState())
	// Example response:
	// submitted batch predict job for model "publishers/google/models/gemini-2.0-flash-001"
	// job id: "projects/.../locations/.../batchPredictionJobs/1234567890000000000"
	// job state: JOB_STATE_PENDING

	for {
		time.Sleep(5 * time.Second)

		job, err := client.GetBatchPredictionJob(ctx, &aiplatformpb.GetBatchPredictionJobRequest{
			Name: fullJobId,
		})
		if err != nil {
			return fmt.Errorf("error: couldn't get updated job state: %w", err)
		}

		if job.GetEndTime() != nil {
			fmt.Fprintf(w, "batch predict job finished with state %s\n", job.GetState())
			break
		} else {
			fmt.Fprintf(w, "batch predict job is running... job state is %s\n", job.GetState())
		}
	}

	return nil
}

Input BigQuery

import (
	"context"
	"fmt"
	"io"
	"time"

	aiplatform "cloud.google.com/go/aiplatform/apiv1"
	aiplatformpb "cloud.google.com/go/aiplatform/apiv1/aiplatformpb"

	"google.golang.org/api/option"
	"google.golang.org/protobuf/types/known/structpb"
)

// batchPredictBQ submits a batch prediction job using BigQuery data source as its input
func batchPredictBQ(w io.Writer, projectID, location string, inputURI string, outputURI string) error {
	// location  := "us-central1"
	// inputURI  := "bq://storage-samples.generative_ai.batch_requests_for_multimodal_input"
	// outputURI := "bq://<cloud-project-name>.<dataset-name>.<table-name>"
	modelName := "gemini-2.0-flash-001"
	jobName := "batch-predict-bq-test-001"

	ctx := context.Background()
	apiEndpoint := fmt.Sprintf("%s-aiplatform.googleapis.com:443", location)
	client, err := aiplatform.NewJobClient(ctx, option.WithEndpoint(apiEndpoint))
	if err != nil {
		return fmt.Errorf("unable to create aiplatform client: %w", err)
	}
	defer client.Close()

	modelParameters, err := structpb.NewValue(map[string]interface{}{
		"temperature":     0.2,
		"maxOutputTokens": 200,
	})
	if err != nil {
		return fmt.Errorf("unable to convert model parameters to protobuf value: %w", err)
	}

	req := &aiplatformpb.CreateBatchPredictionJobRequest{
		Parent: fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		BatchPredictionJob: &aiplatformpb.BatchPredictionJob{
			DisplayName:     jobName,
			Model:           fmt.Sprintf("publishers/google/models/%s", modelName),
			ModelParameters: modelParameters,
			// Check the API reference for `BatchPredictionJob` for supported input and output formats:
			// https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.BatchPredictionJob
			InputConfig: &aiplatformpb.BatchPredictionJob_InputConfig{
				Source: &aiplatformpb.BatchPredictionJob_InputConfig_BigquerySource{
					BigquerySource: &aiplatformpb.BigQuerySource{
						InputUri: inputURI,
					},
				},
				InstancesFormat: "bigquery",
			},

			OutputConfig: &aiplatformpb.BatchPredictionJob_OutputConfig{
				Destination: &aiplatformpb.BatchPredictionJob_OutputConfig_BigqueryDestination{
					BigqueryDestination: &aiplatformpb.BigQueryDestination{
						OutputUri: outputURI,
					},
				},
				PredictionsFormat: "bigquery",
			},
		},
	}

	job, err := client.CreateBatchPredictionJob(ctx, req)
	if err != nil {
		return err
	}
	fullJobId := job.GetName()
	fmt.Fprintf(w, "submitted batch predict job for model %q\n", job.GetModel())
	fmt.Fprintf(w, "job id: %q\n", fullJobId)
	fmt.Fprintf(w, "job state: %s\n", job.GetState())
	// Example response:
	// submitted batch predict job for model "publishers/google/models/gemini-2.0-flash-001"
	// job id: "projects/.../locations/.../batchPredictionJobs/1234567890000000000"
	// job state: JOB_STATE_PENDING

	for {
		time.Sleep(5 * time.Second)

		job, err := client.GetBatchPredictionJob(ctx, &aiplatformpb.GetBatchPredictionJobRequest{
			Name: fullJobId,
		})
		if err != nil {
			return fmt.Errorf("error: couldn't get updated job state: %w", err)
		}

		if job.GetEndTime() != nil {
			fmt.Fprintf(w, "batch predict job finished with state %s\n", job.GetState())
			break
		} else {
			fmt.Fprintf(w, "batch predict job is running... job state is %s\n", job.GetState())
		}
	}

	return nil
}

Recupera output batch

Al termine di un'attività di previsione batch, l'output viene archiviato nel bucket Cloud Storage o nella tabella BigQuery specificati nella richiesta.

Passaggi successivi