Create text embeddings

Generates vector embeddings for single or multiple text inputs. Returns floating-point vectors along with token usage statistics.

POST /api/v1/llm/embeddings

Python (SDK)

Python

from mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.embeddings.embed(input="The quick brown fox jumps over the lazy dog.", model="auto", encoding_format="float")

    # Handle response
    print(res)

200

{
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023,
        -0.0091,
        0.0156,
        -0.0042,
        0.0089
      ],
      "index": 0
    }
  ],
  "model": "auto",
  "object": "list",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Authorizations

Authorization · string · header · required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Headers

X-On-Behalf-Of · string

Optional external end-user identifier forwarded by the API gateway.

Body

application/json

Request parameters for creating embeddings. Generates vector representations of the input text(s).

input · string string[] · required

The input text or array of texts to generate embeddings for. Can be a single string or an array of strings. Note: batch size and input length limits vary by model. See GET /embeddings/models for model-specific limits.

Required string length: 1 - 100000

model · string · required

ID of the model to use for generating embeddings. Use provider:model format. See GET /embeddings/models for available models and their limits.

Minimum string length: 1

dimensions · integer

The number of dimensions the resulting output embeddings should have. Only supported in certain models.

Required range: 1 <= x <= 9007199254740991

encoding_format · enum<string> · default: float

The format to return the embeddings in. Can be either 'float' (array of numbers) or 'base64' (base64-encoded binary).

Available options: float, base64

user · string

A unique identifier representing your end-user.

Response

200 - application/json

OK

Response from the embeddings endpoint containing the generated embeddings and usage information.

data · object[] · required

A list of embedding objects. Each object contains the embedding vector as an array of floating point numbers or base64-encoded string representing the semantic meaning of the input text.

Show child attributes

model · string · required

The model used for generating the embeddings

object · any · default: list

usage · object

Usage statistics for the embeddings request

Show child attributes