PII detection identifies sensitive personal information in user inputs before they reach an LLM pipeline, helping prevent token use, privacy leaks, and downstream policy violations. section 13.3.1
A production implementation can:
- Combine PII detection with other input validators, such as competitor and policy checks. section 13.3.1
- Target entities such as email addresses, credit-card numbers, and Social Security numbers. section 13.3.1
- Redact detected values or raise a validation failure, depending on the configured failure action. section 13.3.1
Guardrails AI input guard
Configure a Guardrails AI guard with a PII validator, call it on each user query, and return the validated output only after validation succeeds. A redacted email can then continue through the LLM pipeline without exposing the original value. section 13.3.1
Listing 13.13 Validating input by using Guardrails AI for safety
from guardrails import Guard
from guardrails.hub import CompetitorCheck, GuardrailsPII
from guardrails.types.on_fail import OnFailAction
DATAKRYPT_COMPETITORS = [
"AWS KMS", "Azure Key Vault", "Google Cloud KMS",
"HashiCorp Vault", "CyberArk", "Thales", "Venafi"
]
input_guard = Guard().use_many( #1
CompetitorCheck(
DATAKRYPT_COMPETITORS,
on_fail=OnFailAction.EXCEPTION #2
),
GuardrailsPII(
entities=["EMAIL_ADDRESS", "CREDIT_CARD", "SSN"],
on_fail=OnFailAction.FIX #3
),
)
def validate_user_input(user_input: str) -> str:
"""Validate and sanitize user input before processing"""
try:
result = input_guard.validate(user_input)#4
return result.validated_output #5
except Exception as e:
logger.warning(f"Input validation failed: {e}")
raise ValueError( #6
"Input contains prohibited content") #6
Inspect the complete validator configuration and validation function, including entity selection, failure actions, exception handling, and sanitized output. section 13.3.1
