guardrails-ai
Add field level granularity to reask capability
Imagine we have a guard output structure with 10 fields defined in it and each field has validators. If we make an LLM call and validate that guard, and 9 fields pass validation but 1 fails, then in the current system, we reask for the entire object and substitute the entire object after validation. This is expensive both for the LLM and in terms of the amount of validation we run. Instead, if we could reask ONLY for the missing field and substitute it in after validation, that's much cheaper.
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 14 days.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
This issue was closed because it has been stalled for 14 days with no activity.
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 14 days.