CohereRerankRetriever

class CohereRerankRetriever(BaseRetriever):

An implementation of the BaseRetriever using the Cohere Re-ranking model.

Attributes: model_name (str): The model name to use for re-ranking. api_key (Optional[str]): The API key for authenticating with the Cohere service.

References: https://txt.cohere.com/rerank/

init

def __init__(
    self,
    model_name: str = 'rerank-multilingual-v2.0',
    api_key: Optional[str] = None
):

Initializes an instance of the CohereRerankRetriever. This constructor sets up a client for interacting with the Cohere API using the specified model name and API key. If the API key is not provided, it attempts to retrieve it from the COHERE_API_KEY environment variable.

Parameters:

  • model_name (str): The name of the model to be used for re-ranking. Defaults to ‘rerank-multilingual-v2.0’.
  • api_key (Optional[str]): The API key for authenticating requests to the Cohere API. If not provided, the method will attempt to retrieve the key from the environment variable ‘COHERE_API_KEY’.

query

def query(
    self,
    query: str,
    retrieved_result: List[Dict[str, Any]],
    top_k: int = DEFAULT_TOP_K_RESULTS
):

Queries and compiles results using the Cohere re-ranking model.

Parameters:

  • query (str): Query string for information retriever.
  • retrieved_result (List[Dict[str, Any]]): The content to be re-ranked, should be the output from BaseRetriever like VectorRetriever.
  • top_k (int, optional): The number of top results to return during retriever. Must be a positive integer. Defaults to DEFAULT_TOP_K_RESULTS.

Returns:

List[Dict[str, Any]]: Concatenated list of the query results.