I encountered an error: openai. error. AuthenticationError Invalid token (request id: 20240204142954xxxxxxxxxxxxxxxxxxx)

[joonk685]

Confirm this is an issue with the Python library and not an underlying OpenAI API

• This is an issue with the Python library

Describe the bug

When I call the openai API, it may be normal for the first 1-6 hours, but then as long as I send a request to gpt-3.5 turbo, an AuthenticationError Invalid token (request id: 20240204142954xxxxxxxxxxxxxxxxxxx) will occur. When I restart my django service, it returns to a normal state, which I am very puzzled about

To Reproduce

1. Call the openai interface
2. Maintain call frequency and wait for a few hours
3. An invalid token with an error occurred
4. When restarting django, everything becomes normal again

Code snippets

response = openai.ChatCompletion.create(
                    model="gpt-3.5-turbo-1106",
                    stream=True,
                    messages=conversation_list,
                    timeout=120
                )
                for data in response:
                    if "content" in data["choices"][0]["delta"]:
                        content = data["choices"][0]["delta"]["content"]
                        print(content, end='')

OS

linux

Python version

Python v3.9.2

Library version

openai v0.28

[joonk685]

I have resolved this issue. My problem lies in using an old version of the OpenAI library to call dell-e-3
Once called in this way, all subsequent calls to the GPT interface will encounter errors. Therefore, execute pip install -- upgrade openai to upgrade openai and migrate the code to the latest writing method to complete the upgrade