Problems with Vision model

[VitoJanko]

Hello,
Tried using this library and had good success with it using gpt-4-1106-preview model. However, when using gpt-4-vision-preview, it crashes with the error message:

openai.BadRequestError: Error code: 400 - {'error': {'message': '2 validation errors for Request\nbody -> function_call\n extra fields not permitted (type=value_error.extra)\nbody -> functions\n extra fields not permitted (type=value_error.extra)', 'type': 'invalid_request_error', 'param': None, 'code': None}}

Is there some workaround for that? I might be missing something obvious

[jxnl]

Please share your code snippet

[jxnl]

https://jxnl.github.io/instructor/concepts/patching/?h=#markdown-json-mode

make sure you use the right now as function calling is not supported for vision models

[VitoJanko]

This seems to work, thanks!