RetrievalToolkit

class RetrievalToolkit(BaseToolkit):

A class representing a toolkit for information retrieval.

This class provides methods for retrieving information from a local vector storage system based on a specified query.

init

def __init__(
    self,
    auto_retriever: Optional[AutoRetriever] = None,
    timeout: Optional[float] = None
):

Initializes a new instance of the RetrievalToolkit class.

information_retrieval

def information_retrieval(
    self,
    query: str,
    contents: Union[str, List[str]],
    top_k: int = Constants.DEFAULT_TOP_K_RESULTS,
    similarity_threshold: float = Constants.DEFAULT_SIMILARITY_THRESHOLD
):

Retrieves information from a local vector storage based on the specified query. This function connects to a local vector storage system and retrieves relevant information by processing the input query. It is essential to use this function when the answer to a question requires external knowledge sources.

Parameters:

  • query (str): The question or query for which an answer is required.
  • contents (Union[str, List[str]]): Local file paths, remote URLs or string contents.
  • top_k (int, optional): The number of top results to return during retrieve. Must be a positive integer. Defaults to DEFAULT_TOP_K_RESULTS.
  • similarity_threshold (float, optional): The similarity threshold for filtering results. Defaults to DEFAULT_SIMILARITY_THRESHOLD.

Returns:

str: The information retrieved in response to the query, aggregated and formatted as a string.

get_tools

def get_tools(self):

Returns:

List[FunctionTool]: A list of FunctionTool objects representing the functions in the toolkit.