Error code: 500 - {'error': {'message': 'The server had an error

API
1

All of my APIs are currently down using the Assistants API. I can see the messages are added to the thread but when my serverless functions attempt to run the thread we get:

Error code: 500 - {‘error’: {‘message’: ‘The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID req_… in your email.)’, ‘type’: ‘server_error’, ‘param’: None, ‘code’: None}}

1 Like
2

Yep. Can confirm: assistant with code interpreter and not vector store - run fails.:

>>>run = client.beta.threads.runs.create_and_poll(
        thread_id=thread.id,
        assistant_id=ass,
        poll_interval_ms=2000)

Traceback (most recent call last):
  File "<pyshell#7>", line 1, in <module>
    run = client.beta.threads.runs.create_and_poll(
  File "C:\Program Files\Python313\Lib\warnings.py", line 637, in wrapper
    return arg(*args, **kwargs)
  File "C:\Program Files\Python313\Lib\site-packages\openai\resources\beta\threads\runs\runs.py", line 831, in create_and_poll
    run = self.create(  # pyright: ignore[reportDeprecated]
  File "C:\Program Files\Python313\Lib\warnings.py", line 637, in wrapper
    return arg(*args, **kwargs)
  File "C:\Program Files\Python313\Lib\site-packages\openai\_utils\_utils.py", line 287, in wrapper
    return func(*args, **kwargs)
  File "C:\Program Files\Python313\Lib\site-packages\openai\resources\beta\threads\runs\runs.py", line 569, in create
    return self._post(
  File "C:\Program Files\Python313\Lib\site-packages\openai\_base_client.py", line 1259, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
  File "C:\Program Files\Python313\Lib\site-packages\openai\_base_client.py", line 1047, in request
    raise self._make_status_error_from_response(err.response) from None
openai.InternalServerError: Error code: 500 - {'error': {'message': 'The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID req_9f927ba0110c74a03f49cb92f2f86e10 in your email.)', 'type': 'server_error', 'param': None, 'code': None}}
1 Like
3

I was unfortunately on a customer call with them trialing a product that uses the Assistants API. I told them there is down-time but I am in an industry with little tolerance for that. Hopefully OpenAI can get this fixed ASAP.

4

If you’ve been employing the SDK, it’s been dumping this for a while as a reminder not to build with this:

-DeprecationWarning: The Assistants API is deprecated in favor of the Responses API

The OpenAI library giving the same advice against Assistants I did Nov 2023…

That doesn’t help when vector stores is also down platform-wide (again).

I just had success with an Assistant run with no tools, no temperature tweaks, gpt-4.

5

@OpenAI_Support shared an update that the issue is resolved now.

In case you are still experiencing issues, you can share them here. Otherwise this topic will close in a day.

6

This topic was automatically closed 24 hours after the last reply. New replies are no longer allowed.