Gemini 모델로 텍스트 일괄 예측

Gemini 모델을 사용하여 일괄 텍스트 예측을 실행하고 출력 위치를 반환합니다.

더 살펴보기

이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.

코드 샘플

Go

이 샘플을 사용해 보기 전에 Vertex AI 빠른 시작: 클라이언트 라이브러리 사용Go 설정 안내를 따르세요. 자세한 내용은 Vertex AI Go API 참고 문서를 참조하세요.

Vertex AI에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

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-1.5-pro-002"
	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-1.5-pro-002"
	// 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
}

Python

이 샘플을 사용해 보기 전에 Vertex AI 빠른 시작: 클라이언트 라이브러리 사용Python 설정 안내를 따르세요. 자세한 내용은 Vertex AI Python API 참고 문서를 참조하세요.

Vertex AI에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

import time
import vertexai

from vertexai.batch_prediction import BatchPredictionJob

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

# Initialize vertexai
vertexai.init(project=PROJECT_ID, location="us-central1")

input_uri = "gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl"

# Submit a batch prediction job with Gemini model
batch_prediction_job = BatchPredictionJob.submit(
    source_model="gemini-1.5-flash-002",
    input_dataset=input_uri,
    output_uri_prefix=output_uri,
)

# Check job status
print(f"Job resource name: {batch_prediction_job.resource_name}")
print(f"Model resource name with the job: {batch_prediction_job.model_name}")
print(f"Job state: {batch_prediction_job.state.name}")

# Refresh the job until complete
while not batch_prediction_job.has_ended:
    time.sleep(5)
    batch_prediction_job.refresh()

# Check if the job succeeds
if batch_prediction_job.has_succeeded:
    print("Job succeeded!")
else:
    print(f"Job failed: {batch_prediction_job.error}")

# Check the location of the output
print(f"Job output location: {batch_prediction_job.output_location}")

# Example response:
#  Job output location: gs://your-bucket/gen-ai-batch-prediction/prediction-model-year-month-day-hour:minute:second.12345

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저를 참조하세요.