semantic_router.encoders.jina

This file contains the JinaEncoder class which is used to encode text using Jina

jina_to_list

def jina_to_list(embeds: CreateEmbeddingResponse) -> list[list[float]]

Convert a Jina embedding response to a list of embeddings.

Arguments:

• embeds (CreateEmbeddingResponse): The embedding response returned by the Jina API.

Returns:

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

JinaEncoder Objects

class JinaEncoder(DenseEncoder, AsymmetricDenseMixin)

Class to encode text using Jina. Requires a Jina API key from https://jina.ai/api-keys/

Jina exposes an OpenAI-compatible embeddings endpoint, so this encoder drives it with the OpenAI SDK pointed at https://api.jina.ai/v1 rather than depending on LiteLLM.

__init__

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

Initialize the JinaEncoder.

Arguments:

• name (str): The name of the embedding model to use such as "jina-embeddings-v3".
• api_key (str): The Jina API key, can also be set via the JINA_API_KEY or JINA_AI_API_KEY environment variable.
• score_threshold (float): The score threshold for the embeddings.
• base_url (str): Override the Jina API base URL, can also be set via the JINA_BASE_URL or JINA_AI_API_BASE environment variable.

Raises:

• ValueError: If no API key is provided or found in the environment.

__call__

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

Encode a list of text documents into embeddings using Jina.

Arguments:

• docs (list[Any]): List of text documents to encode.

Returns:

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

acall

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

Encode a list of text documents into embeddings using Jina asynchronously.

Arguments:

• docs (list[Any]): List of text documents to encode.

Returns:

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