Text embeddings

Embeddings for Text (textembedding-gecko) is the name for the model that supports text embeddings. Text embeddings are a NLP technique that converts textual data into numerical vectors that can be processed by machine learning algorithms, especially large models. These vector representations are designed to capture the semantic meaning and context of the words they represent.

There are a few versions available for embeddings. textembedding-gecko@003 is the newest stable embedding model with enhanced AI quality, and textembedding-gecko-multilingual@001 is a model optimized for a wide range of non-English languages.

To explore this model in the console, see the Embeddings for Text model card in the Model Garden.
Go to the Model Garden

Use cases

Semantic Search: Text embeddings can be used to represent both the user's query and the universe of documents in a high-dimensional vector space. Documents that are more semantically similar to the user's query will have a shorter distance in the vector space, and can be ranked higher in the search results.

Text Classification: Training a model that maps the text embeddings to the correct category labels (e.g., cat vs. dog, spam vs. not spam). Once the model is trained, it can be used to classify new text inputs into one or more categories based on their embeddings.

HTTP request

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/textembedding-gecko:predict

Model versions

To use the latest model version, specify with the @latest suffix, for example textembedding-gecko@latest.

To use a stable model version, specify the model version number, for example textembedding-gecko@003. Each stable version is available for six months after the release date of the subsequent stable version.

The following table contains the available stable model versions:

textembedding-gecko model Release date Discontinuation date
textembedding-gecko@003 December 12, 2023 Not applicable
textembedding-gecko@002 November 2, 2023 October 9, 2024
textembedding-gecko-multilingual@001 November 2, 2023 Not applicable
textembedding-gecko@001 June 7, 2023 October 9, 2024
text-embedding-preview-0409 April 9, 2024 To be updated to a stable version.
text-multilingual-embedding-preview-0409 April 9, 2024 To be updated to a stable version.

For more information, see Model versions and lifecycle.

Request body

{
  "instances": [
    { 
      "task_type": "RETRIEVAL_DOCUMENT",
      "title": "document title",
      "content": "I would like embeddings for this text!"
    },
  ]
}

The Vertex AI PaLM Embedding API performs online (real-time) predictions to get embeddings from input text.

The API accepts a maximum of 3,072 input tokens and outputs 768-dimensional vector embeddings. Use the following parameters for the text embeddings model textembedding-gecko. For more information, see Text embeddings overview.

Parameter Description Acceptable values

content

The text that you want to generate embeddings for. Text

task_type

The `task_type` parameter is defined as the intended downstream application to help the model produce better quality embeddings. It is a string that can take on one of the following values. RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING, QUESTION_ANSWERING, FACT_VERIFICATION.

title

The title for the embedding. Text

Sample request

REST

To test a text prompt by using the Vertex AI API, send a POST request to the publisher model endpoint.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • TEXT: The text that you want to generate embeddings for.

HTTP method and URL: 

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/textembedding-gecko@003:predict

Request JSON body: 

{
  "instances": [
    { "content": "TEXT"}
  ],
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command: 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/textembedding-gecko@003:predict"

PowerShell

Save the request body in a file named request.json, and execute the following command: 

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/textembedding-gecko@003:predict" | Select-Object -Expand Content

You should receive a JSON response similar to the sample response.

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation. 

from typing import List

from vertexai.language_models import TextEmbeddingInput, TextEmbeddingModel


def embed_text(
    texts: List[str] = ["banana muffins? ", "banana bread? banana muffins?"],
    task: str = "RETRIEVAL_DOCUMENT",
    model_name: str = "textembedding-gecko@003",
) -> List[List[float]]:
    """Embeds texts with a pre-trained, foundational model."""
    model = TextEmbeddingModel.from_pretrained(model_name)
    inputs = [TextEmbeddingInput(text, task) for text in texts]
    embeddings = model.get_embeddings(inputs)
    return [embedding.values for embedding in embeddings]

Node.js

Before trying this sample, follow the Node.js setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Node.js API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

async function main(
  project,
  model = 'textembedding-gecko@003',
  texts = 'banana bread?;banana muffins?',
  task = 'RETRIEVAL_DOCUMENT',
  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 match = apiEndpoint.match(/(?<Location>\w+-\w+)/);
  const location = match ? match.groups.Location : 'us-centra11';
  const endpoint = `projects/${project}/locations/${location}/publishers/google/models/${model}`;

  async function callPredict() {
    const instances = texts
      .split(';')
      .map(e => helpers.toValue({content: e, taskType: task}));
    const request = {endpoint, instances};
    const client = new PredictionServiceClient(clientOptions);
    const [response] = await client.predict(request);
    console.log('Got predict response');
    const predictions = response.predictions;
    for (const prediction of predictions) {
      const embeddings = prediction.structValue.fields.embeddings;
      const values = embeddings.structValue.fields.values.listValue.values;
      console.log('Got prediction: ' + JSON.stringify(values));
    }
  }

  callPredict();
}

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Java API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

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.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 = "textembedding-gecko@003";
    predictTextEmbeddings(
        endpoint,
        project,
        model,
        List.of("banana bread?", "banana muffins?"),
        "RETRIEVAL_DOCUMENT");
  }

  // 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)
      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);

    // You can use this prediction service client for multiple requests.
    try (PredictionServiceClient client = PredictionServiceClient.create(settings)) {
      PredictRequest.Builder request =
          PredictRequest.newBuilder().setEndpoint(endpointName.toString());
      for (int i = 0; i < texts.size(); i++) {
        request.addInstances(
            Value.newBuilder()
                .setStructValue(
                    Struct.newBuilder()
                        .putFields("content", valueOf(texts.get(i)))
                        .putFields("taskType", valueOf(task))
                        .build()));
      }
      PredictResponse response = client.predict(request.build());
      List<List<Float>> floats = new ArrayList<>();
      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();
  }
}

Response body

{
  "predictions": [
    {
      "embeddings": {
        "statistics": {
          "truncated": boolean,
          "token_count": integer
        },
        "values": [ number ]
      }
    }
  ]
}
Response element Description
embeddings The result generated from input text.
statistics The statistics computed from the input text.
truncated Indicates if the input text was longer than max allowed tokens and truncated.
tokenCount Number of tokens of the input text.
values The values field contains the embedding vectors corresponding to the words in the input text.

Sample response

{
  "predictions": [
    {
      "embeddings": {
        "values": [
          0.0058424929156899452,
          0.011848051100969315,
          0.032247550785541534,
          -0.031829461455345154,
          -0.055369812995195389,
          ...
        ],
        "statistics": {
          "token_count": 4,
          "truncated": false
        }
      }
    }
  ]
}