Yandex Cloud
Search
Contact UsGet started
  • Pricing
  • Customer Stories
  • Documentation
  • Blog
  • All Services
  • System Status
    • Featured
    • Infrastructure & Network
    • Data Platform
    • Containers
    • Developer tools
    • Serverless
    • Security
    • Monitoring & Resources
    • AI for business
    • Business tools
  • All Solutions
    • By industry
    • By use case
    • Economics and Pricing
    • Security
    • Technical Support
    • Start testing with double trial credits
    • Cloud credits to scale your IT product
    • Gateway to Russia
    • Cloud for Startups
    • Center for Technologies and Society
    • Yandex Cloud Partner program
  • Pricing
  • Customer Stories
  • Documentation
  • Blog
© 2025 Direct Cursus Technology L.L.C.
Yandex AI Studio
    • About Yandex AI Studio
    • Yandex Workflows
    • Quotas and limits
    • Terms and definitions
  • Compatibility with OpenAI
    • Overview
    • API authentication
        • Overview
          • Overview
          • TextEmbedding
  • Access management
  • Pricing policy
  • Audit Trails events
  • Public materials
  • Release notes

In this article:

  • gRPC request
  • TextEmbeddingRequest
  • TextEmbeddingResponse
  1. API references
  2. Embeddings API
  3. gRPC
  4. Embeddings
  5. TextEmbedding

Foundation Models Embedding API, gRPC: EmbeddingsService.TextEmbedding

Written by
Yandex Cloud
Updated at April 24, 2025
  • gRPC request
  • TextEmbeddingRequest
  • TextEmbeddingResponse

A method for obtaining embeddings from text data.

gRPC requestgRPC request

rpc TextEmbedding (TextEmbeddingRequest) returns (TextEmbeddingResponse)

TextEmbeddingRequestTextEmbeddingRequest

{
  "model_uri": "string",
  "text": "string",
  "dim": "google.protobuf.Int64Value"
}

Request for the service to obtain text embeddings.

Field

Description

model_uri

string

The model URI to be used for obtaining text embeddings.

text

string

The input text for which the embedding is requested.

dim

google.protobuf.Int64Value

Optional parameter to specify embedding dimension for models that support multi-dimensional outputs

TextEmbeddingResponseTextEmbeddingResponse

{
  "embedding": [
    "double"
  ],
  "num_tokens": "int64",
  "model_version": "string"
}

Response containing generated text embedding.

Field

Description

embedding[]

double

A repeated list of double values representing the embedding.

num_tokens

int64

The number of tokens in the input text.

model_version

string

The model version changes with each new releases.

Was the article helpful?

Previous
Overview
Next
Overview
© 2025 Direct Cursus Technology L.L.C.