README.md

metadata

license: mit

Table of Contents

• LCToolFlow
  • LCToolFlow
    • instantiate_from_config
    • run

LCToolFlow

LCToolFlow Objects

class LCToolFlow(AtomicFlow)

A flow that runs a tool using langchain. For example, a tool could be to excute a query with the duckduckgo search engine.

Configuration Parameters:

• name (str): The name of the flow. Default: "search"
• description (str): A description of the flow. This description is used to generate the help message of the flow. Default: "useful when you need to look for the answer online, especially for recent events."
• keep_raw_response (bool): If True, the raw response of the tool is kept. Default: False
• clear_flow_namespase_on_run_end (bool): If True, the flow namespace is cleared at the end of the run. Default: False
• backend (Dict[str, Any]): The configuration of the backend. Default: langchain.tools.DuckDuckGoSearchRun
• Other parameters are inherited from the default configuration of AtomicFlow (see AtomicFlow)

Input Interface:

• query (str): the query to run the tool on

Output Interface:

• observation (str): the observation returned by the tool

Arguments:

• backend (BaseTool): The backend of the flow. It is a tool that is run by the flow. (e.g. duckduckgo search engine)
• \**kwargs: Additional arguments to pass to the flow. See :class:aiflows.base_flows.AtomicFlow for more details.

instantiate_from_config

@classmethod
def instantiate_from_config(cls, config: Dict[str, Any]) -> LCToolFlow

This method instantiates the flow from a configuration file

Arguments:

• config (Dict[str, Any]): The configuration of the flow.

Returns:

LCToolFlow: The instantiated flow.

run

def run(input_message: FlowMessage)

This method runs the flow. It runs the backend on the input data.

Arguments:

• input_message (FlowMessage): The input message of the flow.