使用 Vertex AI 中的生成式 AI 建立嵌入

使用生成式 AI 建構嵌入內容

深入探索

如需包含這個程式碼範例的詳細說明文件，請參閱下列內容：

• Text embeddings API

程式碼範例

Java

在試用這個範例之前，請先按照Java使用用戶端程式庫的 Vertex AI 快速入門中的操作說明進行設定。 詳情請參閱 Vertex AI Java API 參考說明文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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

在試用這個範例之前，請先按照Node.js使用用戶端程式庫的 Vertex AI 快速入門中的操作說明進行設定。 詳情請參閱 Vertex AI Node.js API 參考說明文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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();
}

後續步驟

如要搜尋及篩選其他 Google Cloud 產品的程式碼範例，請參閱Google Cloud 範例瀏覽器。