langchain_community.chat_models.gpt_router.acompletion_with_retry

async langchain_community.chat_models.gpt_router.acompletion_with_retry(llm: GPTRouter, models_priority_list: List[GPTRouterModel], run_manager: Optional[AsyncCallbackManagerForLLMRun] = None, **kwargs: Any) → Union[GenerationResponse, AsyncGenerator[ChunkedGenerationResponse, None]]

使用tenacity重试异步完成调用。

参数

• llm (GPTRouter) –

• models_priority_list (List[GPTRouterModel]) –

• run_manager (Optional[AsyncCallbackManagerForLLMRun]) –

• kwargs (Any) –

返回类型

Union[GenerationResponse, AsyncGenerator[ChunkedGenerationResponse, None]]