swarms/examples/agents/3rd_party_agents/auto_gen.py

import os
from typing import Any, Dict, Optional

from autogen import ConversableAgent
from loguru import logger

from swarms import Agent


class AutogenAgentWrapper(Agent):
    """
    Wrapper class for the ConversableAgent that provides additional functionality.
    """

    def __init__(
        self,
        name: str,
        llm_config: Dict[str, Any],
        *args: Any,
        **kwargs: Any,
    ):
        """
        Initialize the AutogenAgentWrapper.

        Args:
            name (str): The name of the agent.
            llm_config (Dict[str, Any]): The configuration for the ConversableAgent.
            *args: Additional positional arguments.
            **kwargs: Additional keyword arguments.
        """
        super().__init__(*args, **kwargs)
        self.name = name
        self.autogen_agent = ConversableAgent(
            name=name,
            llm_config=llm_config,
            code_execution_config=False,
            function_map=None,
            human_input_mode="NEVER",
        )

    def run(
        self, task: str, *args: Any, **kwargs: Any
    ) -> Optional[str]:
        """
        Run the AutogenAgentWrapper.

        Args:
            task (str): The task to be performed by the agent.
            *args: Additional positional arguments.
            **kwargs: Additional keyword arguments.

        Returns:
            Optional[str]: The response generated by the agent, or None if an error occurred.
        """
        try:
            messages = [{"content": task, "role": "user"}]
            response = self.autogen_agent.generate_reply(messages)
            logger.info("Task: %s, Response: %s", task, response)
            return response
        except Exception as e:
            logger.error("An error occurred: %s", str(e))
            return None


llm_config = {
    "config_list": [
        {
            "model": "gpt-4",
            "api_key": os.environ.get("OPENAI_API_KEY"),
        }
    ]
}

autogen_wrapper = AutogenAgentWrapper("AutogenAssistant", llm_config)
result = autogen_wrapper.run("Tell me a joke about programming.")
print(result)