Text Embeddings Inference

OpenAI compatible route. Returns a 424 status code if the model is not an embedding model.

Changed on
post/v1/embeddings

Request

  • The document declares no server URL.
  • Auth
    none declared

Request body

dimensionsinteger nullable
encoding_format'float' | 'base64'
modelstring nullable
userstring nullable

Example request

{
  "model": "null",
  "user": "null"
}

Response

Embeddings

modelstring required
objectstring required

Example response

{
  "data": [
    {
      "object": "embedding"
    }
  ],
  "model": "thenlper/gte-base",
  "object": "list"
}

Changes

    • warning

      added the new Empty enum value to the response property for the response status

    • warning

      added the new Empty enum value to the response property for the response status

    • warning

      added the new Empty enum value to the response property for the response status

    • warning

      added the new Empty enum value to the response property for the response status

    • info

      added the new optional request property

    • info

      added the non-success response with the status

    • info

      endpoint added