Your comment has an unnecessary and overly negative tone to it that doesn't do this tech justice. These approaches are totally valid and can get you great results. An LLM is just a component in a pipeline. I deployed many of these in production without a hiccup.
Guidance (the industry term for "constraining" the model output) is only there to ensure the output follows a particular grammar. If you need JSON to fit a particular schema or format, then you can always validate it. In case of validation failure you can always pass the JSON and the validation result back to the LLM for it to correct it.
Guidance (the industry term for "constraining" the model output) is only there to ensure the output follows a particular grammar. If you need JSON to fit a particular schema or format, then you can always validate it. In case of validation failure you can always pass the JSON and the validation result back to the LLM for it to correct it.