Task Generation Cookbook

You can also check this cookbook in colab here

In this tutorial, we will focus on demonstrating how to use the task module in the CAMEL framework. We will guide you through creating, evolving, and decomposing tasks to illustrate how the task module can be utilized for efficient task management in agent-based systems.

Sections included:

• Setting up a ChatAgent with the CAMEL framework

• Creating a Task and evolving it with the agent using TaskManager

• Task decomposition using the CAMEL task module

Let’s go step by step!

Step 1: Import necessary CAMEL modules

First, we need to import the required CAMEL modules for creating the ChatAgent and handling tasks.

!pip install "camel-ai==0.2.9"

from camel.agents import ChatAgent
from camel.configs import ChatGPTConfig
from camel.messages import BaseMessage
from camel.models import ModelFactory
from camel.tasks import (
    Task,
    TaskManager,
)
from camel.types import (
    ModelPlatformType,
    ModelType,
)

Set your OpenAI key

import os
from getpass import getpass

# Prompt for the API key securely
openai_api_key = getpass('Enter your API key: ')
os.environ["OPENAI_API_KEY"] = openai_api_key

Enter your API key: ··········

Step 2: Set up the Large Language Model (LLM)

Next, we set up the model configuration. We are using a GPT-4O Mini in this case for our assistant agent. The configuration is designed to ensure the agent’s behavior remains deterministic by setting temperature=0.0, meaning no randomness will be introduced in the responses.

# Create the model using the configuration
model = ModelFactory.create(
    model_platform=ModelPlatformType.OPENAI,
    model_type=ModelType.GPT_4O_MINI,
    model_config_dict=ChatGPTConfig(temperature=0.0).as_dict(), # [Optional] the config for model
)

Step 3: Initialize the ChatAgent

We now create a ChatAgent using the previously defined model. This agent will interact with tasks in the CAMEL framework, following the role of a personal math tutor and programmer.

# Set up the assistant's system message
assistant_sys_msg = BaseMessage.make_user_message(
    role_name="Teacher",
    content="You are a personal math tutor and programmer.",
)

# Initialize the ChatAgent
agent = ChatAgent(assistant_sys_msg, model)
agent.reset()  # Reset the agent's internal state

Step 4: Evolve and decompose tasks

We now create a Task that represents a math problem for the assistant to solve. In this case, we are asking the assistant to calculate how much Weng earned for babysitting based on her hourly rate and the time she worked.

# Create a Task for the agent to solve
task = Task(
    content="Weng earns $12 an hour for babysitting. Yesterday, she just did 51 minutes of babysitting. How much did she earn?",
    id="0",  # Task identifier
)

# Print the task to see the original form
print(task.to_string())

Task 0: Weng earns $12 an hour for babysitting. Yesterday, she just did 51 minutes of babysitting. How much did she earn?

Evolve the Task

We can evolve the task using the TaskManager, which allows the agent to potentially update or reframe the task based on its internal logic and context.

task_manager = TaskManager(task)

evolved_task = task_manager.evolve(task, agent=agent)
if evolved_task is not None:
    print(evolved_task.to_string())
else:
    print("Evolved task is None.")

Task 0.0: Weng earns $12 an hour for babysitting. Yesterday, she babysat for 1 hour and 45 minutes. If she also received a bonus of $5 for exceptional service, how much did she earn in total?

Decompose the Task

Sometimes, tasks are complex and need to be broken down into smaller subtasks. We use decompose() to allow the agent to split the original task into simpler parts.

new_tasks = task.decompose(agent=agent)
for t in new_tasks:
    print(t.to_string())

Task 0.0: Convert the babysitting time from minutes to hours.

Task 0.1: Calculate the earnings based on the hourly rate of $12 and the converted time in hours.

Task 0.2: Present the final earnings amount clearly.