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