Error GPT 3.5 turbo Response 401: {"detail":"Unauthorized"}

[BokDan93]

I added it yesterday .HAR File to the folder ./harder, the model is working, today the error Response 401: {"detail":"Unauthorized"} What to do? Do I need to add a file every time? Is it possible to do as before and not use this file?

[hlohaus]

You could install and use nodriver. It performs the same function as the previous webdriver.

[BokDan93]

Could you please tell me how to do this or provide a link to the tutorial?

[hlohaus]

The installation of Nodriver can be achieved through the following command:

pip install -U nodriver

No further configuration is required.

[iG8R]

Please, could you elaborate how to use nodriver to make WebUI start working instead of bringing up:

Using OpenaiChat provider and gpt-3.5-turbo model
ERROR:root:Response 401: {"detail":"Could not parse your authentication token. Please try signing in again."}
Traceback (most recent call last):
  File "c:\gpt4free\venv\Lib\site-packages\g4f\gui\server\api.py", line 125, in _create_response_stream
    for chunk in ChatCompletion.create(**kwargs):
  File "c:\gpt4free\venv\Lib\site-packages\g4f\providers\base_provider.py", line 208, in create_completion
    yield loop.run_until_complete(await_callback(gen.__anext__))
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\asyncio\base_events.py", line 664, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "c:\gpt4free\venv\Lib\site-packages\g4f\providers\base_provider.py", line 40, in await_callback
    return await callback()
           ^^^^^^^^^^^^^^^^
  File "c:\gpt4free\venv\Lib\site-packages\g4f\Provider\needs_auth\OpenaiChat.py", line 381, in create_async_generator
    await raise_for_status(response)
  File "c:\gpt4free\venv\Lib\site-packages\g4f\requests\raise_for_status.py", line 28, in raise_for_status_async
    raise ResponseStatusError(f"Response {response.status}: {message}")
g4f.errors.ResponseStatusError: Response 401: {"detail":"Could not parse your authentication token. Please try signing in again."}
127.0.0.1 - - [10/Apr/2024 15:03:45] "POST /backend-api/v2/conversation HTTP/1.1" 200 -
INFO:werkzeug:127.0.0.1 - - [10/Apr/2024 15:03:45] "POST /backend-api/v2/conversation HTTP/1.1" 200 -

[BokDan93]

Thanks, I'll try!

Could you reflect this point somewhere in the tutorials, at least where we are talking about the .har file? Thank you in advance

[iG8R]

PS. Forgot to mention that even with nodriver installed, the aforementioned error still occurs.

[hlohaus]

I have resolved the authentication token parsing issue in the GUI.

Nodriver should now automatically open a browser window.

[iG8R]

Now (0.2.9.3 version) it starts work fine with the presence of the har file, but without it only arises the following error:

Using OpenaiChat provider and gpt-3.5-turbo model
127.0.0.1 - - [10/Apr/2024 18:24:50] "GET /static/img/user.png HTTP/1.1" 200 -
ERROR:root:
Traceback (most recent call last):
  File "c:\gpt4free\venv\Lib\site-packages\g4f\gui\server\api.py", line 125, in _create_response_stream
    for chunk in ChatCompletion.create(**kwargs):
  File "c:\gpt4free\venv\Lib\site-packages\g4f\providers\base_provider.py", line 211, in create_completion
    yield loop.run_until_complete(await_callback(gen.__anext__))
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\asyncio\base_events.py", line 664, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "c:\gpt4free\venv\Lib\site-packages\g4f\providers\base_provider.py", line 40, in await_callback
    return await callback()
           ^^^^^^^^^^^^^^^^
  File "c:\gpt4free\venv\Lib\site-packages\g4f\Provider\needs_auth\OpenaiChat.py", line 371, in create_async_generator
    await cls.nodriver_access_token()
  File "c:\gpt4free\venv\Lib\site-packages\g4f\Provider\needs_auth\OpenaiChat.py", line 584, in nodriver_access_token
    browser = await uc.start(user_data_dir=user_data_dir)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\gpt4free\venv\Lib\site-packages\nodriver\core\util.py", line 74, in start
    return await Browser.create(config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\gpt4free\venv\Lib\site-packages\nodriver\core\browser.py", line 87, in create
    await instance.start()
  File "c:\gpt4free\venv\Lib\site-packages\nodriver\core\browser.py", line 312, in start
    await asyncio.create_subprocess_exec(
  File "C:\Python312\Lib\asyncio\subprocess.py", line 222, in create_subprocess_exec
    transport, protocol = await loop.subprocess_exec(
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\asyncio\base_events.py", line 1708, in subprocess_exec
    transport = await self._make_subprocess_transport(
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\asyncio\base_events.py", line 502, in _make_subprocess_transport
    raise NotImplementedError
NotImplementedError
127.0.0.1 - - [10/Apr/2024 18:24:51] "POST /backend-api/v2/conversation HTTP/1.1" 200 -
INFO:werkzeug:127.0.0.1 - - [10/Apr/2024 18:24:51] "POST /backend-api/v2/conversation HTTP/1.1" 200 -

[BokDan93]

Error after installation pip install -U nodriver: list index out of range

[github-actions[bot]]

Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again.

[hlohaus]

Do you still have this error?

[BokDan93]

yes(

[github-actions[bot]]

Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again.

[hlohaus]

The validity period of an OpenAI Chat .har file is limited to one day.

[github-actions[bot]]

Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again.

[github-actions[bot]]

Closing due to inactivity.