cohere_client

Cohere ModelClient integration.

Classes

CohereAPIClient([api_key])

A component wrapper for the Cohere API.

class CohereAPIClient(api_key: str | None = None)

Bases: ModelClient

A component wrapper for the Cohere API.

Visit https://docs.cohere.com/ for more api details.

References: - Cohere reranker: https://docs.cohere.com/reference/rerank

Tested Cohere models: 6/16/2024 - rerank-english-v3.0, rerank-multilingual-v3.0, rerank-english-v2.0, rerank-multilingual-v2.0

Note

For all ModelClient integration, such as CohereAPIClient, if you want to subclass CohereAPIClient, you need to import it from the module directly.

from adalflow.components.model_client.cohere_client import CohereAPIClient

instead of using the lazy import with:

from adalflow.components.model_client import CohereAPIClient

init_sync_client()

init_async_client()

convert_inputs_to_api_kwargs(input: Any | None = None, model_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED) → Dict

For rerank model, expect model_kwargs to have the following keys:

model: str, query: str, documents: List[str], top_n: int,

call(api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED)

Subclass use this to call the API with the sync client. model_type: this decides which API, such as chat.completions or embeddings for OpenAI. api_kwargs: all the arguments that the API call needs, subclass should implement this method.

Additionally in subclass you can implement the error handling and retry logic here. See OpenAIClient for example.

async acall(api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED)

Subclass use this to call the API with the async client.