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]] [source]¶
Use tenacity to retry the async completion call.