Skip to main content

agentchat.contrib.agent_optimizer

execute_func​

def execute_func(name, packages, code, **args)

The wrapper for generated functions.

AgentOptimizer​

class AgentOptimizer()

Base class for optimizing AutoGen agents. Specifically, it is used to optimize the functions used in the agent. More information could be found in the following paper: https://arxiv.org/abs/2402.11359.

__init__​

def __init__(max_actions_per_step: int,
             llm_config: dict,
             optimizer_model: Optional[str] = "gpt-4-1106-preview")

(These APIs are experimental and may change in the future.)

Arguments:

  • max_actions_per_step int - the maximum number of actions that the optimizer can take in one step.
  • llm_config dict - llm inference configuration. Please refer to OpenAIWrapper.create for available options. When using OpenAI or Azure OpenAI endpoints, please specify a non-empty 'model' either in llm_config or in each config of 'config_list' in llm_config.
  • optimizer_model - the model used for the optimizer.

record_one_conversation​

def record_one_conversation(conversation_history: List[Dict],
                            is_satisfied: bool = None)

record one conversation history.

Arguments:

  • conversation_history List[Dict] - the chat messages of the conversation.
  • is_satisfied bool - whether the user is satisfied with the solution. If it is none, the user will be asked to input the satisfaction.

step​

def step()

One step of training. It will return register_for_llm and register_for_executor at each iteration, which are subsequently utilized to update the assistant and executor agents, respectively. See example: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_agentoptimizer.ipynb

reset_optimizer​

def reset_optimizer()

reset the optimizer.