텍스트 임베딩(생성형 AI) 가져오기

임베딩 모델을 사용하여 텍스트 스니펫에 대한 텍스트 임베딩을 가져옵니다.

코드 샘플

Java

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

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

import static java.util.stream.Collectors.toList;

import com.google.cloud.aiplatform.v1.EndpointName;
import com.google.cloud.aiplatform.v1.PredictRequest;
import com.google.cloud.aiplatform.v1.PredictResponse;
import com.google.cloud.aiplatform.v1.PredictionServiceClient;
import com.google.cloud.aiplatform.v1.PredictionServiceSettings;
import com.google.protobuf.Struct;
import com.google.protobuf.Value;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.OptionalInt;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class PredictTextEmbeddingsSample {
  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    // Details about text embedding request structure and supported models are available in:
    // https://cloud.google.com/vertex-ai/docs/generative-ai/embeddings/get-text-embeddings
    String endpoint = "us-central1-aiplatform.googleapis.com:443";
    String project = "YOUR_PROJECT_ID";
    String model = "gemini-embedding-001";
    predictTextEmbeddings(
        endpoint,
        project,
        model,
        List.of("banana bread?", "banana muffins?"),
        "QUESTION_ANSWERING",
        OptionalInt.of(3072));
  }

  // Gets text embeddings from a pretrained, foundational model.
  public static List<List<Float>> predictTextEmbeddings(
      String endpoint,
      String project,
      String model,
      List<String> texts,
      String task,
      OptionalInt outputDimensionality)
      throws IOException {
    PredictionServiceSettings settings =
        PredictionServiceSettings.newBuilder().setEndpoint(endpoint).build();
    Matcher matcher = Pattern.compile("^(?<Location>\\w+-\\w+)").matcher(endpoint);
    String location = matcher.matches() ? matcher.group("Location") : "us-central1";
    EndpointName endpointName =
        EndpointName.ofProjectLocationPublisherModelName(project, location, "google", model);

    List<List<Float>> floats = new ArrayList<>();
    // You can use this prediction service client for multiple requests.
    try (PredictionServiceClient client = PredictionServiceClient.create(settings)) {
      // gemini-embedding-001 takes one input at a time.
      for (int i = 0; i < texts.size(); i++) {
        PredictRequest.Builder request = 
            PredictRequest.newBuilder().setEndpoint(endpointName.toString());
        if (outputDimensionality.isPresent()) {
          request.setParameters(
              Value.newBuilder()
                  .setStructValue(
                      Struct.newBuilder()
                          .putFields(
                              "outputDimensionality", valueOf(outputDimensionality.getAsInt()))
                          .build()));
        }
        request.addInstances(
            Value.newBuilder()
                .setStructValue(
                    Struct.newBuilder()
                        .putFields("content", valueOf(texts.get(i)))
                        .putFields("task_type", valueOf(task))
                        .build()));
        PredictResponse response = client.predict(request.build());

        for (Value prediction : response.getPredictionsList()) {
          Value embeddings = prediction.getStructValue().getFieldsOrThrow("embeddings");
          Value values = embeddings.getStructValue().getFieldsOrThrow("values");
          floats.add(
              values.getListValue().getValuesList().stream()
                  .map(Value::getNumberValue)
                  .map(Double::floatValue)
                  .collect(toList()));
        }
      }
      return floats;
    }
  }

  private static Value valueOf(String s) {
    return Value.newBuilder().setStringValue(s).build();
  }

  private static Value valueOf(int n) {
    return Value.newBuilder().setNumberValue(n).build();
  }
}

Node.js

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

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

async function main(
  project,
  model = 'gemini-embedding-001',
  texts = 'banana bread?;banana muffins?',
  task = 'QUESTION_ANSWERING',
  dimensionality = 0,
  apiEndpoint = 'us-central1-aiplatform.googleapis.com'
) {
  const aiplatform = require('@google-cloud/aiplatform');
  const {PredictionServiceClient} = aiplatform.v1;
  const {helpers} = aiplatform; // helps construct protobuf.Value objects.
  const clientOptions = {apiEndpoint: apiEndpoint};
  const location = 'us-central1';
  const endpoint = `projects/${project}/locations/${location}/publishers/google/models/${model}`;

  async function callPredict() {
    const instances = texts
      .split(';')
      .map(e => helpers.toValue({content: e, task_type: task}));

    const client = new PredictionServiceClient(clientOptions);
    const parameters = helpers.toValue(
      dimensionality > 0 ? {outputDimensionality: parseInt(dimensionality)} : {}
    );
    const allEmbeddings = []
    // gemini-embedding-001 takes one input at a time.
    for (const instance of instances) {
      const request = {endpoint, instances: [instance], parameters};
      const [response] = await client.predict(request);
      const predictions = response.predictions;

      const embeddings = predictions.map(p => {
        const embeddingsProto = p.structValue.fields.embeddings;
        const valuesProto = embeddingsProto.structValue.fields.values;
        return valuesProto.listValue.values.map(v => v.numberValue);
      });

      allEmbeddings.push(embeddings[0])
    }


    console.log('Got embeddings: \n' + JSON.stringify(allEmbeddings));
  }

  callPredict();
}

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저 참조하기