Skip to content

Planning Agent

Overview

The PlanningAgent class is a utility agent within the AI Refinery SDK designed to assist in the design of a realistic plan for any given task. The Planning Agent scans the different interactions between the user and all the agents and design the plan required to achieve the different goals provided by the user.

Implementation

The PlanningAgent class is responsible for generating a realistic plan based based on the interaction data.

Template YAML configuration

agent_class: PlanningAgent
agent_name: <name of the agent>
agent_description: <description of the agent>
config:
  output_style: <"markdown" or "conversational" or "html">  # Optional field
  contexts:  # Optional field
    - "date"
    - "chat_history" # the chat history upto a certain number of rounds
    - "env_variable"
    - "relevant_chat_history" # the chat history that is relevant to the current query
  self_reflection_config:  # Optional. Configuration for self-reflection.
    self_reflection: <true or false>   # Whether to enable self-reflection for this agent. Default is false.
    max_attempts: <number>  # Maximum number of times the agent can perform self-reflection. Default is 2.
    response_selection_mode: <"best" | "aggregate" | "auto">  # Strategy used to generate the final response after reaching max_attempts. Default is "auto".
    return_internal_reflection_msg: <true or false>   # Whether to return internal reflection messages. Default is false.