Hello. I opened an issue in github (I cannot post links, so it’s Issue #372 in openai/openai-openapi repo).
But maybe I will get more feedback here.
I believe it would be a great addition to the API to be able to specify further constraints to the StructuredOutput, because it makes the use of gpt much more predictable and less error-prone.
I would like to know if this is in the roadmap or not. Thanks.