Foundation Models Embedding API, REST: Embeddings.TextEmbedding

Статья создана

Обновлена 8 августа 2025 г.

A method for obtaining embeddings from text data.

HTTP request

POST https://llm.api.cloud.yandex.net/foundationModels/v1/textEmbedding

{
  "modelUri": "string",
  "text": "string",
  "dim": "string"
}

Request for the service to obtain text embeddings.

Field	Description
modelUri	string The model URI to be used for obtaining text embeddings.
text	string The input text for which the embedding is requested.
dim	string (int64) Optional parameter to specify embedding dimension for models that support multi-dimensional outputs

HTTP Code: 200 - OK

{
  "embedding": [
    "string"
  ],
  "numTokens": "string",
  "modelVersion": "string"
}

Response containing generated text embedding.

Field	Description
embedding[]	string A repeated list of double values representing the embedding.
numTokens	string (int64) The number of tokens in the input text.
modelVersion	string The model version changes with each new releases.