Open FredrikNoren opened 1 month ago
I have tested with the default extract-to-root
and none
with some surprising results. For a complex zod schema using extract-to-root
schema uses 3 times as many input tokens than none
. Your mileage may vary if using on simple schema. I have not observed any downsides when using none
.
Confirm this is a feature request for the Node library and not the underlying OpenAI API.
Describe the feature or improvement you're requesting
The "extract-to-root" strategy is not working for my types, but I tried changing the strategy to "none" which seems to work. It would be nice to be able to just pass down which strategy to use through
zodFunction
Additional context
No response