Embeddings

Overview

Embeddings API.

Available Operations

• create - Embeddings

create

Embeddings

Example Usage

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.embeddings.create(model="mistral-embed", inputs=[
        "Embed this sentence.",
        "As well as this one.",
    ])

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description	Example
model	str	:heavy_check_mark:	ID of the model to use.	mistral-embed
inputs	models.EmbeddingRequestInputs	:heavy_check_mark:	Text to embed.	[ "Embed this sentence.", "As well as this one." ]
metadata	Dict[str, Any]	:heavy_minus_sign:	N/A
output_dimension	OptionalNullable[int]	:heavy_minus_sign:	The dimension of the output embeddings when feature available. If not provided, a default output dimension will be used.
output_dtype	Optional[models.EmbeddingDtype]	:heavy_minus_sign:	N/A
encoding_format	Optional[models.EncodingFormat]	:heavy_minus_sign:	N/A
retries	Optional[utils.RetryConfig]	:heavy_minus_sign:	Configuration to override the default retry behavior of the client.

Response

models.EmbeddingResponse

Errors

Error Type	Status Code	Content Type
errors.HTTPValidationError	422	application/json
errors.SDKError	4XX, 5XX	*/*