autogen.agentchat.contrib.agent_optimizer.AgentOptimizer

AgentOptimizer

AgentOptimizer(
    max_actions_per_step: int,
    llm_config: LLMConfig | dict[str, Any],
    optimizer_model: str | None = 'gpt-4-1106-preview'
)

Base class for optimizing AG2 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.
(These APIs are experimental and may change in the future.)

Parameters:

Name	Description
max_actions_per_step	Type: int
llm_config	Type: LLMConfig | dict[str, typing.Any]
optimizer_model	Type: str | None Default: ‘gpt-4-1106-preview’

Instance Methods

record_one_conversation

record_one_conversation(
    self,
    conversation_history: list[dict[str, Any]],
    is_satisfied: bool = None
) -> 

Record one conversation history.

Parameters:

Name	Description
conversation_history	the chat messages of the conversation. Type: list[dict[str, typing.Any]]
is_satisfied	whether the user is satisfied with the solution. If it is none, the user will be asked to input the satisfaction. Type: bool Default: None

reset_optimizer

reset_optimizer(self) -> 

Reset the optimizer.

step

step(self) -> 

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/ag2ai/ag2/blob/main/notebook/agentchat_agentoptimizer.ipynb