You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Step 1: Have you search for this issue before posting it?
yes
Step 2: Describe your environment
running docker, version latest
Step 3: Describe the problem:
Describe the bug
set GPT Evaluater GPT Model: the GPT model to use. to "o1-mini" gives the following error:
"ERROR | GPTEvaluator | Invalid GPT request: Error when running request with model o1-mini (invalid request): Error code: 400 - {'error': {'message': "Unsupported value: 'messages[0].role' does not support 'system' with this model.", 'type': 'invalid_request_error', 'param': 'messages[0].role', 'code': 'unsupported_value'}}
Expected behavior
It does not give an error, as with gpt-4, gpt-4o etc.
Steps to reproduce:
Navigate to Confiuration of GPTEvaluator
Set GPT Model to "o1-mini"
Observed Results:
What happened? an error occured using chat gpt
What did you expect to happen? no error occurs and chatgpt works as expected
Relevant code exceptions or logs:
"ERROR | GPTEvaluator | Invalid GPT request: Error when running request with model o1-mini (invalid request): Error code: 400 - {'error': {'message': "Unsupported value: 'messages[0].role' does not support 'system' with this model.", 'type': 'invalid_request_error', 'param': 'messages[0].role', 'code': 'unsupported_value'}}
The text was updated successfully, but these errors were encountered:
Thanks for reporting this issue @sam-semillia
Unfortunately, as o1-mini doesn't yet support system prompts, it can't be used for predictions. The next version of OctoBot will display a better error message.
Step 1: Have you search for this issue before posting it?
yes
Step 2: Describe your environment
running docker, version latest
Step 3: Describe the problem:
Describe the bug
set GPT Evaluater GPT Model: the GPT model to use. to "o1-mini" gives the following error:
"ERROR | GPTEvaluator | Invalid GPT request: Error when running request with model o1-mini (invalid request): Error code: 400 - {'error': {'message': "Unsupported value: 'messages[0].role' does not support 'system' with this model.", 'type': 'invalid_request_error', 'param': 'messages[0].role', 'code': 'unsupported_value'}}
Expected behavior
It does not give an error, as with gpt-4, gpt-4o etc.
Steps to reproduce:
Observed Results:
Relevant code exceptions or logs:
"ERROR | GPTEvaluator | Invalid GPT request: Error when running request with model o1-mini (invalid request): Error code: 400 - {'error': {'message': "Unsupported value: 'messages[0].role' does not support 'system' with this model.", 'type': 'invalid_request_error', 'param': 'messages[0].role', 'code': 'unsupported_value'}}
The text was updated successfully, but these errors were encountered: