completion_with_retry#
- langchain_community.chat_models.gpt_router.completion_with_retry(llm: GPTRouter, models_priority_list: List[GPTRouterModel], run_manager: CallbackManagerForLLMRun | None = None, **kwargs: Any) GenerationResponse | Generator[ChunkedGenerationResponse, None, None] [source]#
Use tenacity to retry the completion call.
- Parameters:
llm (GPTRouter) –
models_priority_list (List[GPTRouterModel]) –
run_manager (Optional[CallbackManagerForLLMRun]) –
kwargs (Any) –
- Return type:
Union[GenerationResponse, Generator[ChunkedGenerationResponse, None, None]]