Text Embeddings API

from __future__ import annotations

from vertexai.language_models import TextEmbeddingInput, TextEmbeddingModel


def embed_text() -> list[list[float]]:
    """Embeds texts with a pre-trained, foundational model.

    Returns:
        A list of lists containing the embedding vectors for each input text
    """

    # A list of texts to be embedded.
    texts = ["banana muffins? ", "banana bread? banana muffins?"]
    # The dimensionality of the output embeddings.
    dimensionality = 3072
    # The task type for embedding. Check the available tasks in the model's documentation.
    task = "RETRIEVAL_DOCUMENT"

    model = TextEmbeddingModel.from_pretrained("gemini-embedding-001")
    kwargs = dict(output_dimensionality=dimensionality) if dimensionality else {}

    embeddings = []
    # gemini-embedding-001 takes one input at a time
    for text in texts:
        text_input = TextEmbeddingInput(text, task)
        embedding = model.get_embeddings([text_input], **kwargs)
        print(embedding)
        # Example response:
        # [[0.006135190837085247, -0.01462465338408947, 0.004978656303137541, ...]]
        embeddings.append(embedding[0].values)

    return embeddings

import (
	"context"
	"fmt"
	"io"

	aiplatform "cloud.google.com/go/aiplatform/apiv1"
	"cloud.google.com/go/aiplatform/apiv1/aiplatformpb"

	"google.golang.org/api/option"
	"google.golang.org/protobuf/types/known/structpb"
)

// embedTexts shows how embeddings are set for gemini-embedding-001 model
func embedTexts(w io.Writer, project, location string) error {
	// location := "us-central1"
	ctx := context.Background()

	apiEndpoint := fmt.Sprintf("%s-aiplatform.googleapis.com:443", location)
	dimensionality := 3072
	model := "gemini-embedding-001"
	texts := []string{"banana muffins? ", "banana bread? banana muffins?"}

	client, err := aiplatform.NewPredictionClient(ctx, option.WithEndpoint(apiEndpoint))
	if err != nil {
		return err
	}
	defer client.Close()

	endpoint := fmt.Sprintf("projects/%s/locations/%s/publishers/google/models/%s", project, location, model)
	allEmbeddings := make([][]float32, 0, len(texts))
	// gemini-embedding-001 takes 1 input at a time
	for _, text := range texts {
		instances := make([]*structpb.Value, 1)
		instances[0] = structpb.NewStructValue(&structpb.Struct{
			Fields: map[string]*structpb.Value{
				"content":   structpb.NewStringValue(text),
				"task_type": structpb.NewStringValue("QUESTION_ANSWERING"),
			},
		})

		params := structpb.NewStructValue(&structpb.Struct{
			Fields: map[string]*structpb.Value{
				"outputDimensionality": structpb.NewNumberValue(float64(dimensionality)),
			},
		})

		req := &aiplatformpb.PredictRequest{
			Endpoint:   endpoint,
			Instances:  instances,
			Parameters: params,
		}
		resp, err := client.Predict(ctx, req)
		if err != nil {
			return err
		}

		// Process the prediction for the single text
		// The response will contain one prediction because we sent one instance.
		if len(resp.Predictions) == 0 {
			return fmt.Errorf("no predictions returned for text \"%s\"", text)
		}

		prediction := resp.Predictions[0]
		embeddingValues := prediction.GetStructValue().Fields["embeddings"].GetStructValue().Fields["values"].GetListValue().Values

		currentEmbedding := make([]float32, len(embeddingValues))
		for j, value := range embeddingValues {
			currentEmbedding[j] = float32(value.GetNumberValue())
		}
		allEmbeddings = append(allEmbeddings, currentEmbedding)
	}

	if len(allEmbeddings) > 0 {
		fmt.Fprintf(w, "Dimensionality: %d. Embeddings length: %d", len(allEmbeddings[0]), len(allEmbeddings))
	} else {
		fmt.Fprintln(w, "No texts were processed.")
	}
	return nil
}

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();
  }
}

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();
}