semantic_router.encoders.mistral

This file contains the MistralEncoder class which is used to encode text using MistralAI

def mistral_to_list(embeds: EmbeddingResponse) -> list[list[float]]

Convert a Mistral embedding response to a list of embeddings. Arguments:

Returns: list[list[float]]: One embedding per input document.

MistralEncoder Objects

class MistralEncoder(DenseEncoder, AsymmetricDenseMixin)

Class to encode text using MistralAI and SDK. Requires a MistralAI API key from https://console.mistral.ai/api-keys/

def __init__(name: str | None = None,
             mistralai_api_key: str | None = None,
             score_threshold: float = 0.4)

Initialize the MistralEncoder. Arguments:

def __call__(docs: list[Any], **kwargs) -> list[list[float]]

Encode a list of text documents into embeddings using MistralAI. Arguments:

Returns: list[list[float]]: List of embeddings for each document.

async def acall(docs: list[Any], **kwargs) -> list[list[float]]

Encode a list of text documents into embeddings using MistralAI asynchronously. Arguments:

Returns: list[list[float]]: List of embeddings for each document.