Obtenir des représentations vectorielles continues de texte (IA generative)

import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1beta1.EndpointName;
import com.google.cloud.aiplatform.v1beta1.PredictResponse;
import com.google.cloud.aiplatform.v1beta1.PredictionServiceClient;
import com.google.cloud.aiplatform.v1beta1.PredictionServiceSettings;
import com.google.protobuf.Value;
import com.google.protobuf.util.JsonFormat;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

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:
    // http://cloud.go888ogle.com.fqhub.com/vertex-ai/docs/generative-ai/embeddings/get-text-embeddings
    String instance = "{ \"content\": \"What is life?\"}";
    String project = "YOUR_PROJECT_ID";
    String location = "us-central1";
    String publisher = "google";
    String model = "textembedding-gecko@001";

    predictTextEmbeddings(instance, project, location, publisher, model);
  }

  // Get text embeddings from a supported embedding model
  public static void predictTextEmbeddings(
      String instance, String project, String location, String publisher, String model)
      throws IOException {
    String endpoint = String.format("%s-aiplatform.googleapis.com:443", location);
    PredictionServiceSettings predictionServiceSettings =
        PredictionServiceSettings.newBuilder()
            .setEndpoint(endpoint)
            .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 (PredictionServiceClient predictionServiceClient =
        PredictionServiceClient.create(predictionServiceSettings)) {
      EndpointName endpointName =
          EndpointName.ofProjectLocationPublisherModelName(project, location, publisher, model);

      // Use Value.Builder to convert instance to a dynamically typed value that can be
      // processed by the service.
      Value.Builder instanceValue = Value.newBuilder();
      JsonFormat.parser().merge(instance, instanceValue);
      List<Value> instances = new ArrayList<>();
      instances.add(instanceValue.build());

      PredictResponse predictResponse =
          predictionServiceClient.predict(endpointName, instances, ValueConverter.EMPTY_VALUE);
      System.out.println("Predict Response");
      for (Value prediction : predictResponse.getPredictionsList()) {
        System.out.format("\tPrediction: %s\n", prediction);
      }
    }
  }
}

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 * (Not necessary if passing values as arguments)
 */
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');

// Imports the Google Cloud Prediction service client
const {PredictionServiceClient} = aiplatform.v1;

// Import the helper module for converting arbitrary protobuf.Value objects.
const {helpers} = aiplatform;

// Specifies the location of the api endpoint
const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};

const publisher = 'google';
const model = 'textembedding-gecko@001';

// Instantiates a client
const predictionServiceClient = new PredictionServiceClient(clientOptions);

async function callPredict() {
  // Configure the parent resource
  const endpoint = `projects/${project}/locations/${location}/publishers/${publisher}/models/${model}`;

  const instance = {
    content: 'What is life?',
  };
  const instanceValue = helpers.toValue(instance);
  const instances = [instanceValue];

  const parameter = {
    temperature: 0,
    maxOutputTokens: 256,
    topP: 0,
    topK: 1,
  };
  const parameters = helpers.toValue(parameter);

  const request = {
    endpoint,
    instances,
    parameters,
  };

  // Predict request
  const [response] = await predictionServiceClient.predict(request);
  console.log('Get text embeddings response');
  const predictions = response.predictions;
  console.log('\tPredictions :');
  for (const prediction of predictions) {
    console.log(`\t\tPrediction : ${JSON.stringify(prediction)}`);
  }
}

callPredict();

from vertexai.language_models import TextEmbeddingModel

def text_embedding() -> list:
    """Text embedding with a Large Language Model."""
    model = TextEmbeddingModel.from_pretrained("textembedding-gecko@001")
    embeddings = model.get_embeddings(["What is life?"])
    for embedding in embeddings:
        vector = embedding.values
        print(f"Length of Embedding Vector: {len(vector)}")