I am newbie to use openAI API.
Issue Statement
Since our app only requires language based operation, I only set the permission on those two capabilities.
-
Responses
-
Chat completions
However, when I tested the API calling, the requests failed with this error:
upstream error {
status: 401,
body: '{\n' +
' "error": {\n' +
` "message": "You have insufficient permissions for
this operation. Missing scopes: model.request. Check that you have
the correct role in your organization (Reader, Writer, Owner) and
project (Member, Owner), and if you're using a restricted API key,
that it has the necessary scopes.",\n` +
' "type": "invalid_request_error",\n' +
' "param": null,\n' +
' "code": null\n' +
' }\n' +
'}',
user_id: '---------------'
}
What I found
After some experiments, I noticed that ‘model request’ permission is only granted when I set ‘Model Capabilities’ to ‘request’,
I confirmed this by by hovering over ‘selected permissions’ in the UI.
Current work-around
-
Set ‘Model Capabilities’ option to ‘Request’
-
Set the other options not required in my project to ‘None’
Suggestions
I believe this UI/UX should be improved to bring more developers into the openAI ecosystem.
