langchain_community.chat_models.fireworks.completion_with_retry¶
- langchain_community.chat_models.fireworks.completion_with_retry(llm: ChatFireworks, use_retry: bool, *, run_manager: Optional[CallbackManagerForLLMRun] = None, **kwargs: Any) Any[source]¶
Use tenacity to retry the completion call.
- Parameters
llm (ChatFireworks) –
use_retry (bool) –
run_manager (Optional[CallbackManagerForLLMRun]) –
kwargs (Any) –
- Return type
Any