Prioritizing Responses with Multiple Guardrails on a Single Guard Object

[hodgesz]

I am referring to the documentation to setup multiple guardrails for a single guard object - https://www.guardrailsai.com/docs/hub/how_to_guides/multiple_validators

Is there a way to prioritize the response in the case where multiple guardrails get triggered so that the highest priority guardrail response gets returned? For instance maybe we have a self-harm and PII guardrails and they both trigger, we would like the response for self-harm to come back.

Is that possible in guardrails-ai?

[wylansford]

At the moment no, all guards are run with the same prioritization. You may be able to get some of the info you are looking for by checking the guard history:

 from guardrails import Guard
 from guardrails.hub import RegexMatch, ValidLength

 guard = Guard().use_many(
     ValidLength(min=1, max=128, on_fail="fix"),
     RegexMatch(regex="^[A-Z][a-z]*$", on_fail="fix"),
 )

 result = guard.parse("��Caesar is a great leader")  # Guardrail Fails

 print(guard.history)

It will have some of the information for each guard that is run

[hodgesz]

Appreciate your quick response! Let me try guard.history and see how that works. I will reach back out if I have any more questions.