Table of Contents
HumanStandardInputFlow
log
ToDo: Is there a better fix?
HumanStandardInputFlow Objects
class HumanStandardInputFlow(AtomicFlow)
This class implements a HumanStandardInputFlow. It's used to read input from the user/human. Typically used to get feedback from the user/human.
Configuration Parameters:
name(str): The name of the flow.description(str): A description of the flow. This description is used to generate the help message of the flow. Default: "Reads input from the user's standard input."request_multi_line_input_flag(bool): If True, the user/human is requested to enter a multi-line input. If False, the user/human is requested to enter a single-line input. Default: No defaul, this parameter is required.end_of_input_string(str): The string that the user/human should enter to indicate that the input is finished. This parameter is only used if "request_multi_line_input_flag" is True. Default: "EOI"query_message_prompt_template(JinjaPrompt): The prompt template used to generate the query message. By default its of type aiflows.prompt_template.JinjaPrompt. None of the parameters of the prompt are defined by default and therefore need to be defined if one wants to use the init_human_message_prompt_template. Default parameters are defined in aiflows.prompt_template.jinja2_prompts.JinjaPrompt.The other parameters are inherited from the default configuration of AtomicFlow (see AtomicFlow)
input_interface:
- No Input Interface. By default, the input interface expects no input. But if inputs are expected from the query_message_prompt_template,then the input interface should contain the keys specified in the input_variables of the query_message_prompt_template.
output_interface:
human_input(str): The message inputed from the user/human.
Arguments:
query_message_prompt_template(JinjaPrompt): The prompt template used to generate the query message. Expected if the class is instantiated programmatically.\**kwargs(Dict[str, Any]): The keyword arguments passed to the AtomicFlow constructor. Use to create the flow_config. Includes request_multi_line_input_flag, end_of_input_string, input_keys, description of Configuration Parameters.
instantiate_from_config
@classmethod
def instantiate_from_config(cls, config)
Instantiates the flow from a config file.
Arguments:
config(Dict[str, Any]): The configuration of the flow.
run
def run(input_message: FlowMessage)
Runs the HumanStandardInputFlow. It's used to read input from the user/human's standard input.
Arguments:
input_message(FlowMessage): The input message