langchain_community.chat_models.fireworks.acompletion_with_retry_streaming

async langchain_community.chat_models.fireworks.acompletion_with_retry_streaming(llm: ChatFireworks, use_retry: bool, *, run_manager: Optional[AsyncCallbackManagerForLLMRun] = None, **kwargs: Any) → Any

使用tenacity来重试流的完成调用。

Parameters

• llm (ChatFireworks) –

• use_retry (bool) –

• run_manager (Optional[AsyncCallbackManagerForLLMRun]) –

• kwargs (Any) –

Return type

Any