How to get the final output from the load_summarize_chain async run?

[axiangcoding]

code example here:

async def summary(callback: BaseCallbackHandler):
    llm = AzureChatOpenAI(
        deployment_name=os.environ["OPENAI_GPT35_DEPLOYMENT_NAME"],
    )
    text_splitter = NLTKTextSplitter(chunk_size=1000)
    texts = text_splitter.split_text(content)
    docs = [Document(page_content=t) for t in texts]
    chain = load_summarize_chain(llm, chain_type="map_reduce", verbose=False)
    await chain.arun(docs, callbacks=[callback])

and callback defined here:

class SummaryCallback(BaseCallbackHandler):
    def on_chain_end(self, outputs: Dict[str, Any], *, run_id: UUID, parent_run_id: Optional[UUID] = None,
                     **kwargs: Any) -> Any:
        logger.info(f"on_chain_end: {outputs}, {run_id}, {parent_run_id}, {kwargs}")
        

    def on_tool_end(self, output: str, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) -> Any:
        logger.info(f"on_tool_end: {output}, {run_id}, {parent_run_id}, {kwargs}")
       

    def on_llm_end(self, response: LLMResult, *, run_id: UUID, parent_run_id: Optional[UUID] = None,
                   **kwargs: Any) -> Any:
        logger.info(f"on_llm_end: {response}, {run_id}, {parent_run_id}, {kwargs}")
        

when i test it, console shows:

2023-05-24 08:42:46.143 | INFO     | routers.v1.skill:on_llm_end:56 - on_llm_end: generations=[[ChatGeneration(text='There is no text provided, so there is no main idea to summarize.', generation_info=None, message=AIMessage(content='There is no text provided, so there is no main idea to summarize.', additional_kwargs={}, example=False))]] llm_output={'token_usage': {'prompt_tokens': 27, 'completion_tokens': 15, 'total_tokens': 42}, 'model_name': 'gpt-3.5-turbo'}, b9cb89c9-3e89-4335-93e9-8ac8104f9de1, 08558b5a-399c-4ff8-b64a-5856439df7e0, {}
2023-05-24 08:42:46.144 | INFO     | routers.v1.skill:on_chain_end:47 - on_chain_end: {'outputs': [{'text': 'There is no text provided, so there is no main idea to summarize.'}]}, 08558b5a-399c-4ff8-b64a-5856439df7e0, 4a9fe8e7-dfd9-4c7c-a610-513da156071f, {}
2023-05-24 08:42:48.537 | INFO     | routers.v1.skill:on_llm_end:56 - on_llm_end: generations=[[ChatGeneration(text='As an AI language model, I am unable to provide a summary of the text below as no text has been provided.', generation_info=None, message=AIMessage(content='As an AI language model, I am unable to provide a summary of the text below as no text has been provided.', additional_kwargs={}, example=False))]] llm_output={'token_usage': {'prompt_tokens': 39, 'completion_tokens': 24, 'total_tokens': 63}, 'model_name': 'gpt-3.5-turbo'}, 3471ac9f-2290-494e-a939-406bc7b5b8a1, bfe3f758-1275-4662-a553-5e4889aa3958, {}
2023-05-24 08:42:48.539 | INFO     | routers.v1.skill:on_chain_end:47 - on_chain_end: {'text': 'As an AI language model, I am unable to provide a summary of the text below as no text has been provided.'}, bfe3f758-1275-4662-a553-5e4889aa3958, 12bc5030-dced-4243-a841-be44fa411d03, {}
2023-05-24 08:42:48.539 | INFO     | routers.v1.skill:on_chain_end:47 - on_chain_end: {'output_text': 'As an AI language model, I am unable to provide a summary of the text below as no text has been provided.'}, 12bc5030-dced-4243-a841-be44fa411d03, 4a9fe8e7-dfd9-4c7c-a610-513da156071f, {}
2023-05-24 08:42:48.539 | INFO     | routers.v1.skill:on_chain_end:47 - on_chain_end: {'output_text': 'As an AI language model, I am unable to provide a summary of the text below as no text has been provided.'}, 4a9fe8e7-dfd9-4c7c-a610-513da156071f, None, {}

on_chain_end and on_llm_end printed several times, which one is the final output?