Create Embeddings

POST/v1/embeddings

Authorization

Authorizationstringrequired

Bearer token for API authentication. Format: `Bearer YOUR_API_KEY`

Request Body

modelstringrequired

The model to use for creating embeddings.

Constraints

•Minimum length: 1•Maximum length: 500

inputstring | arrayrequired

Input

Constraints

•Minimum length: 1•Maximum length: 64000•Minimum items: 1•Maximum items: 256

dimensionsinteger

The number of dimensions to use for the embeddings.

Constraints

•Exclusive minimum: 0

promptstring

The prompt to use for the embedding creation.

Constraints

•Minimum length: 1•Maximum length: 32000

normalizedbooleandefault: true

Whether to normalize the embeddings.

encoding_formatEncodingFormat | EncodingFormat[]default: float

The encoding format(s) of the embeddings. Can be a single format or a list of formats.

Response Body

modelstringrequired

The model used

dataEmbedding[] | MultiEncodingEmbedding[]required

The created embeddings.

objectstringdefault: list

The object type of the response

normalizedbooleanrequired

Whether the embeddings are normalized.

encoding_formatEncodingFormat | EncodingFormat[]required

The encoding formats of the embeddings.

dimensionsintegerrequired

The number of dimensions used for the embeddings.

Request

POST/v1/embeddings

from mixedbread import Mixedbread

mxbai = Mixedbread(api_key="YOUR_API_KEY")

response = mxbai.embed(
    model="mixedbread-ai/mxbai-embed-large-v1",
    input=[
        "Who is German and likes bread?",
        "Everybody in Germany.",
    ],
    normalized=True,
    encoding_format="float",
)

print(response.data[0].embedding)

Response

JSON

{
  "model": "mixedbread-ai/mxbai-embed-large-v1",
  "normalized": true,
  "encoding_format": "float",
  "object": "list",
  "data": [
    {
      "embedding": [0.1, 0.2, 0.3],
      "index": 0
    },
    {
      "embedding": [0.4, 0.5, 0.6],
      "index": 1
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}