[Question]: Implement OpenAI compatible API via IONOS

[raikloe]

Describe your problem

Hey I hope you can help me.

I want to add an OpenAI compatible model (Llama 3.1 8B and Llama 3.1 70B) via IONOS. The model can be added but as soon as I try to access it, I get the following error

ERROR: Error code: 401 - 
{
 'httpStatus': 401, 
 'messages': [{
      'errorCode': 'paas-auth-1', 
      'message': 'Unauthorized, wrong or no api key provided to process this request'
   }]
}

However, the authentication is not incorrect. I tested it with the OpenAI Python Library and locally. But unfortunately not via Ragflow.

Maybe it's a bug report instead of just a question?...
Thanks for helping!

[raikloe]

@KevinHuSh If I remove the “Bearer ” in the authentication, i can add the model. However, this cannot be the solution, as the bearer is important in principle.

[raikloe]

@KevinHuSh If I remove the “Bearer ” in the authentication, i can add the model. However, this cannot be the solution, as the bearer is important in principle.

When I am using the API without the "Bearer ", I get the following Error ERROR: 'NoneType' object has no attribute 'split' in my chat. Tested with version 0.17.2-slim

[raikloe]

I would suggest, that we will change the issue type to a bug instead of a question? @KevinHuSh Do you need any other information from my side?

[raikloe]

Issue will closed due to a new bug report