Predicción de texto por lotes con el modelo Gemini usando Google Cloud Storage

Realiza una predicción de texto por lotes con el modelo de Gemini y muestra la ubicación del resultado.

Explora más

Para obtener documentación detallada en la que se incluya esta muestra de código, consulta lo siguiente:

Muestra de código

Go

Antes de probar este ejemplo, sigue las instrucciones de configuración para Go incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Go.

Para autenticarte en Vertex AI, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.

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

	"google.golang.org/genai"
)

// generateBatchPredict runs a batch prediction job using GCS input/output.
func generateBatchPredict(w io.Writer, outputURI string) error {
	// outputURI = "gs://your-bucket/your-prefix"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	// Source file with prompts for prediction
	src := &genai.BatchJobSource{
		Format: "jsonl",
		// Source link: https://storage.cloud.google.com/cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl
		GCSURI: []string{"gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl"},
	}

	// Batch job config with output GCS location
	config := &genai.CreateBatchJobConfig{
		Dest: &genai.BatchJobDestination{
			Format: "jsonl",
			GCSURI: outputURI,
		},
	}
	// To use a tuned model, set the model param to your tuned model using the following format:
	//  modelName:= "projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}
	modelName := "gemini-2.5-flash"
	// See the documentation: https://pkg.go.dev/google.golang.org/genai#Batches.Create
	job, err := client.Batches.Create(ctx, modelName, src, config)
	if err != nil {
		return fmt.Errorf("failed to create batch job: %w", err)
	}

	fmt.Fprintf(w, "Job name: %s\n", job.Name)
	fmt.Fprintf(w, "Job state: %s\n", job.State)
	// Example response:
	//   Job name: projects/{PROJECT_ID}/locations/us-central1/batchPredictionJobs/9876453210000000000
	//   Job state: JOB_STATE_PENDING

	// See the documentation: https://pkg.go.dev/google.golang.org/genai#BatchJob
	completedStates := map[genai.JobState]bool{
		genai.JobStateSucceeded: true,
		genai.JobStateFailed:    true,
		genai.JobStateCancelled: true,
		genai.JobStatePaused:    true,
	}

	for !completedStates[job.State] {
		time.Sleep(30 * time.Second)

		job, err = client.Batches.Get(ctx, job.Name, nil)
		if err != nil {
			return fmt.Errorf("failed to get batch job: %w", err)
		}

		fmt.Fprintf(w, "Job state: %s\n", job.State)
	}

	// Example response:
	//  Job state: JOB_STATE_PENDING
	//  Job state: JOB_STATE_RUNNING
	//  Job state: JOB_STATE_RUNNING
	//  ...
	//  Job state: JOB_STATE_SUCCEEDED

	return nil
}

Java

Antes de probar este ejemplo, sigue las instrucciones de configuración para Java incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Java.


import static com.google.genai.types.JobState.Known.JOB_STATE_CANCELLED;
import static com.google.genai.types.JobState.Known.JOB_STATE_FAILED;
import static com.google.genai.types.JobState.Known.JOB_STATE_PAUSED;
import static com.google.genai.types.JobState.Known.JOB_STATE_SUCCEEDED;

import com.google.genai.Client;
import com.google.genai.types.BatchJob;
import com.google.genai.types.BatchJobDestination;
import com.google.genai.types.BatchJobSource;
import com.google.genai.types.CreateBatchJobConfig;
import com.google.genai.types.GetBatchJobConfig;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.JobState;
import java.util.EnumSet;
import java.util.Optional;
import java.util.Set;
import java.util.concurrent.TimeUnit;

public class BatchPredictionWithGcs {

  public static void main(String[] args) throws InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    // To use a tuned model, set the model param to your tuned model using the following format:
    // modelId = "projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}
    String modelId = "gemini-2.5-flash";
    String outputGcsUri = "gs://your-bucket/your-prefix";
    createBatchJob(modelId, outputGcsUri);
  }

  // Creates a batch prediction job with Google Cloud Storage.
  public static JobState createBatchJob(String modelId, String outputGcsUri)
      throws InterruptedException {
    // Client Initialization. Once created, it can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {
      // See the documentation:
      // https://googleapis.github.io/java-genai/javadoc/com/google/genai/Batches.html
      BatchJobSource batchJobSource =
          BatchJobSource.builder()
              // Source link:
              // https://storage.cloud.google.com/cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl
              .gcsUri("gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl")
              .format("jsonl")
              .build();

      CreateBatchJobConfig batchJobConfig =
          CreateBatchJobConfig.builder()
              .displayName("your-display-name")
              .dest(BatchJobDestination.builder().gcsUri(outputGcsUri).format("jsonl").build())
              .build();

      BatchJob batchJob = client.batches.create(modelId, batchJobSource, batchJobConfig);

      String jobName =
          batchJob.name().orElseThrow(() -> new IllegalStateException("Missing job name"));
      JobState jobState =
          batchJob.state().orElseThrow(() -> new IllegalStateException("Missing job state"));
      System.out.println("Job name: " + jobName);
      System.out.println("Job state: " + jobState);
      // Job name: projects/.../locations/.../batchPredictionJobs/6205497615459549184
      // Job state: JOB_STATE_PENDING

      // See the documentation:
      // https://googleapis.github.io/java-genai/javadoc/com/google/genai/types/BatchJob.html
      Set<JobState.Known> completedStates =
          EnumSet.of(JOB_STATE_SUCCEEDED, JOB_STATE_FAILED, JOB_STATE_CANCELLED, JOB_STATE_PAUSED);

      while (!completedStates.contains(jobState.knownEnum())) {
        TimeUnit.SECONDS.sleep(30);
        batchJob = client.batches.get(jobName, GetBatchJobConfig.builder().build());
        jobState =
            batchJob
                .state()
                .orElseThrow(() -> new IllegalStateException("Missing job state during polling"));
        System.out.println("Job state: " + jobState);
      }
      // Example response:
      // Job state: JOB_STATE_QUEUED
      // Job state: JOB_STATE_RUNNING
      // Job state: JOB_STATE_RUNNING
      // ...
      // Job state: JOB_STATE_SUCCEEDED
      return jobState;
    }
  }
}

Node.js

Antes de probar este ejemplo, sigue las instrucciones de configuración para Node.js incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Node.js.

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION =
  process.env.GOOGLE_CLOUD_LOCATION || 'us-central1';
const OUTPUT_URI = 'gs://your-bucket/your-prefix';

async function runBatchPredictionJob(
  outputUri = OUTPUT_URI,
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
    httpOptions: {
      apiVersion: 'v1',
    },
  });

  // See the documentation: https://googleapis.github.io/js-genai/release_docs/classes/batches.Batches.html
  let job = await 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: {
      dest: outputUri,
    },
  });

  console.log(`Job name: ${job.name}`);
  console.log(`Job state: ${job.state}`);

  // Example response:
  //  Job name: projects/%PROJECT_ID%/locations/us-central1/batchPredictionJobs/9876453210000000000
  //  Job state: JOB_STATE_PENDING

  const completedStates = new Set([
    'JOB_STATE_SUCCEEDED',
    'JOB_STATE_FAILED',
    'JOB_STATE_CANCELLED',
    'JOB_STATE_PAUSED',
  ]);

  while (!completedStates.has(job.state)) {
    await new Promise(resolve => setTimeout(resolve, 30000));
    job = await client.batches.get({name: job.name});
    console.log(`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

  return job.state;
}

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Python.

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

¿Qué sigue?

Si quieres buscar y filtrar muestras de código para otros productos de Google Cloud , consulta el navegador de muestras deGoogle Cloud .

Predicción de texto por lotes con el modelo Gemini usando Google Cloud Storage Organiza tus páginas con colecciones Guarda y categoriza el contenido según tus preferencias.