题意：如何等待 OpenAI 助手的实际回复？（Python OpenAI API）

问题背景：

I am interacting with the openai assistant API (python). so far, it works well. but sometimes the api returns the message i sent to the assistant instead of the assistants reply.

我正在使用 OpenAI 助手 API（Python）进行交互，目前效果不错。但有时 API 返回的是我发送给助手的消息，而不是助手的回复。

from openai import OpenAI
from os import environ


OPEN_API_KEY = environ.get('OPEN_API_KEY')
assistant_id = "xxxxxxx"


client = OpenAI(api_key=OPEN_API_KEY)
assistant = client.beta.assistants.retrieve(assistant_id)


def ask_assistant(message_text): 
    print(f'received message: {message_text}')
    
    thread = client.beta.threads.create()
    
    message = client.beta.threads.messages.create(
        thread_id=thread.id,
        role="user",
        content=message_text
    )

    run = client.beta.threads.runs.create(
        thread_id=thread.id,
        assistant_id=assistant_id
    )
    

    run_retrieve = client.beta.threads.runs.retrieve(
        thread_id=thread.id,
        run_id=run.id
    )

as a hot fix, i implemented a sleep function that waits for 3 seconds before retrieving the reply. this works, but i don't expect it to be the best solution (or reliable at all). any ideas how to wait until the assistant REALLY replied?

作为一个临时解决方案，我实现了一个 sleep 函数，在获取回复前等待 3 秒。这种方法有效，但我不认为这是最好的解决方案（或者完全可靠）。有什么办法可以确保等到助手真正回复吗?

thank you very much.        非常感谢

Update:

This works:        下面的方法有效

from openai import OpenAI
from os import environ


OPEN_API_KEY = environ.get('xxxxx')
assistant_id = "xxxxx"


client = OpenAI(api_key=OPEN_API_KEY)
assistant = client.beta.assistants.retrieve(assistant_id)


def get_answer(run, thread):
    while not run.status == "completed":
        print("Waiting for answer...")
        run = client.beta.threads.runs.retrieve(
            thread_id=thread.id,
            run_id=run.id
        )
        

    messages = client.beta.threads.messages.list(thread.id)
    answer = messages.data[0].content[0].text.value
    
    try:
        answer = messages.data[0].content[0].text.value
    except Exception as e:
        print(e)
        answer = ''
        
    return answer


def ask_assistant(message_text): 
    print(f'sending to assistant: {message_text}')
    thread = client.beta.threads.create()
    
    message = client.beta.threads.messages.create(
        thread_id=thread.id,
        role="user",
        content=message_text
    )

    run = client.beta.threads.runs.create(
        thread_id=thread.id,
        assistant_id=assistant_id
    )
    
    answer = get_answer(run, thread)  
    print(f'assistant response: {answer}')
    return answer
    
    
if __name__ == "__main__":
    ask_assistant('Hello')

问题解决：

This should work:        下面的方式应该有效：

run = openai.beta.threads.runs.create(
  thread_id=thread.id,
  assistant_id=assistant.id
)
print(run)


while run.status !="completed":
  run = openai.beta.threads.runs.retrieve(
    thread_id=thread.id,
    run_id=run.id
  )
  print(run.status)

messages = openai.beta.threads.messages.list(
  thread_id=thread.id
)

print(messages.data[0].content[0].text.value)