langchain_community.chat_models.fireworks
.acompletion_with_retry_streamingΒΆ
- async langchain_community.chat_models.fireworks.acompletion_with_retry_streaming(llm: ChatFireworks, use_retry: bool, *, run_manager: Optional[AsyncCallbackManagerForLLMRun] = None, **kwargs: Any) Any [source]ΒΆ
Use tenacity to retry the completion call for streaming.
- Parameters
llm (ChatFireworks) β
use_retry (bool) β
run_manager (Optional[AsyncCallbackManagerForLLMRun]) β
kwargs (Any) β
- Return type
Any