create_base_retry_decorator#

langchain_core.language_models.llms.create_base_retry_decorator(error_types: List[Type[BaseException]], max_retries: int = 1, run_manager: AsyncCallbackManagerForLLMRun | CallbackManagerForLLMRun | None = None) → Callable[[Any], Any][source]#

Create a retry decorator for a given LLM and provided: a list of error types.

Parameters:

error_types (List[Type[BaseException]]) – List of error types to retry on.
max_retries (int) – Number of retries. Default is 1.
run_manager (AsyncCallbackManagerForLLMRun | CallbackManagerForLLMRun | None) – Callback manager for the run. Default is None.

Returns:

A retry decorator.

Raises:

ValueError – If the cache is not set and cache is True.

Return type:

Callable[[Any], Any]