Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api below:

Text embeddings API | Generative AI on Vertex AI

Stay organized with collections Save and categorize content based on your preferences.

This guide shows you how to use the Text Embeddings API to convert text into numerical vectors. This document covers the following topics:

• Syntax: Call the API using cURL or the Python SDK.
• Request and response: Learn about the request and response parameters for the text embedding models.
• Examples: View a code sample that shows how to embed a string of text.
• What's next: Explore related documentation.

The Text embeddings API converts text into numerical vectors called embeddings. These vector representations capture the semantic meaning and context of the text.

Supported Models:

You can get text embeddings by using the following models:

For superior embedding quality, gemini-embedding-001 is our large model designed to provide the highest performance. Note that gemini-embedding-001 supports one instance per request.

PROJECT_ID = PROJECT_ID
REGION = us-central1
MODEL_ID = MODEL_ID

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${REGION}/publishers/google/models/${MODEL_ID}:predict -d \
  '{
    "instances": [
      ...
    ],
    "parameters": {
      ...
    }
  }'

PROJECT_ID = PROJECT_ID
REGION = us-central1
MODEL_ID = MODEL_ID

import vertexai
from vertexai.language_models import TextEmbeddingModel

vertexai.init(project=PROJECT_ID, location=REGION)

model = TextEmbeddingModel.from_pretrained(MODEL_ID)
embeddings = model.get_embeddings(...)

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

• instances: Required. A list of objects that contain the text to embed. The following fields are supported:
  • content (string): The text to generate embeddings for.
  • task_type (string): Optional. Specifies the intended downstream application to help the model produce better quality embeddings. If you don't specify a value, the default is RETRIEVAL_QUERY. For more information about task types, see Choose an embeddings task type.
  • title (string): Optional. A title for the text content. This field applies only when task_type is RETRIEVAL_DOCUMENT.
• parameters: Optional. An object that contains the following fields:
  • autoTruncate (bool): If true, the input text is truncated if it's longer than the model's maximum length. If false, an error is returned for oversized input. The default is true.
  • outputDimensionality (int): The desired embedding size. If set, the output embeddings are truncated to this dimension.

The following table describes the task_type parameter values and their use cases:

• Retrieval tasks:
  • Query: Use task_type=RETRIEVAL_QUERY for the input text that is a search query.
  • Corpus: Use task_type=RETRIEVAL_DOCUMENT for the input text that is part of the document collection being searched.
• Similarity tasks:
  • Semantic similarity: Use task_type=SEMANTIC_SIMILARITY for both input texts to assess their overall similarity in meaning.
• Note: SEMANTIC_SIMILARITY is not intended for retrieval use cases like document search and information retrieval. For these use cases, use RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, QUESTION_ANSWERING, and FACT_VERIFICATION.

{
  "predictions": [
    {
      "embeddings": {
        "statistics": {
          "truncated": boolean,
          "token_count": integer
        },
        "values": [ number ]
      }
    }
  ]
}

• predictions: A list of objects, where each object corresponds to an input instance from the request. Each object contains the following field:
  • embeddings: The embedding generated from the input text. It contains the following fields:
    • values: A list of floats that represents the embedding vector of the input text.
    • statistics: The statistics computed from the input text. It contains the following fields:
      • truncated (bool): true if the input text was truncated because it was longer than the maximum number of tokens allowed by the model.
      • token_count (int): The number of tokens 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
        }
      }
    }
  ]
}

The following example shows you how to get the embedding for a text string.

After you set up your environment, you can use REST to test a text prompt. The following sample sends a 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. Limit: five texts of up to 2,048 tokens per text for all models except textembedding-gecko@001. The max input token length for textembedding-gecko@001 is 3072. For gemini-embedding-001, each request can only include a single input text. For more information, see Text embedding limits.
• AUTO_TRUNCATE: If set to false, text that exceeds the token limit causes the request to fail. The default value is true.

HTTP method and URL:

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/gemini-embedding-001:predict

Request JSON body:

{
  "instances": [
    { "content": "TEXT"}
  ],
  "parameters": { 
    "autoTruncate": AUTO_TRUNCATE 
  }
}

To send your request, choose one of these options:

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/gemini-embedding-001:predict"

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/gemini-embedding-001:predict" | Select-Object -Expand Content

You should receive a JSON response similar to the following. Note that values has been truncated to save space.

{
  "predictions": [
    {
      "embeddings": {
        "statistics": {
          "truncated": false,
          "token_count": 6
        },
        "values": [ ... ]
      }
    }
  ]
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-2.0-flash). This sample might support other models as well.

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.

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

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.

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.

All text embedding models support English-language text and have been evaluated on it.

The text-multilingual-embedding-002 model also supports the following languages. It has been evaluated on the languages in the Evaluated languages list.

• Evaluated languages: Arabic (ar), Bengali (bn), English (en), Spanish (es), German (de), Persian (fa), Finnish (fi), French (fr), Hindi (hi), Indonesian (id), Japanese (ja), Korean (ko), Russian (ru), Swahili (sw), Telugu (te), Thai (th), Yoruba (yo), Chinese (zh)
• Supported languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusiasn, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Sotho, Spanish, Sundanese, Swahili, Swedish, Tajik, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, West Frisian, Xhosa, Yiddish, Yoruba, Zulu.

The gemini-embedding-001 model supports the following languages:

Arabic, Bengali, Bulgarian, Chinese (Simplified and Traditional), Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Thai, Turkish, Ukrainian, Vietnamese, Afrikaans, Amharic, Assamese, Azerbaijani, Belarusian, Bosnian, Catalan, Cebuano, Corsican, Welsh, Dhivehi, Esperanto, Basque, Persian, Filipino (Tagalog), Frisian, Irish, Scots Gaelic, Galician, Gujarati, Hausa, Hawaiian, Hmong, Haitian Creole, Armenian, Igbo, Icelandic, Javanese, Georgian, Kazakh, Khmer, Kannada, Krio, Kurdish, Kyrgyz, Latin, Luxembourgish, Lao, Malagasy, Maori, Macedonian, Malayalam, Mongolian, Meiteilon (Manipuri), Marathi, Malay, Maltese, Myanmar (Burmese), Nepali, Nyanja (Chichewa), Odia (Oriya), Punjabi, Pashto, Sindhi, Sinhala (Sinhalese), Samoan, Shona, Somali, Albanian, Sesotho, Sundanese, Tamil, Telugu, Tajik, Uyghur, Urdu, Uzbek, Xhosa, Yiddish, Yoruba, Zulu.

To use a current stable model, specify the model version number, for example gemini-embedding-001.

Specifying a model without a version number isn't recommended because it's a legacy pointer to another model and isn't stable.

For more information, see Model versions and lifecycle.

Learn more about text embeddings:

• Text Embeddings

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-08-14 UTC.

[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[],[]]

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4