@cdklabs/generative-ai-cdk-constructs • Docs
@cdklabs/generative-ai-cdk-constructs / bedrock / GuardrailProps
Properties for creating a Guardrail.
readonlyoptionalblockedInputMessaging:string
The message to return when the guardrail blocks a prompt.
"Sorry, your query violates our usage policy."
readonlyoptionalblockedOutputsMessaging:string
The message to return when the guardrail blocks a model response.
"Sorry, I am unable to answer your question because of our usage policy."
readonlyoptionalcontentFilters:ContentFilter[]
The content filters to apply to the guardrail. Note, if one of
readonlyoptionalcontextualGroundingFilters:ContextualGroundingFilter[]
The contextual grounding filters to apply to the guardrail.
readonlyoptionaldeniedTopics:Topic[]
Up to 30 denied topics to block user inputs or model responses associated with the topic.
readonlyoptionaldescription:string
The description of the guardrail.
readonlyoptionalkmsKey:IKey
A custom KMS key to use for encrypting data.
"Your data is encrypted by default with a key that AWS owns and manages for you."
readonlyoptionalmanagedWordListFilters:PROFANITY[]
The managed word filters to apply to the guardrail.
readonlyname:string
The name of the guardrail.
readonlyoptionalpiiFilters:PIIFilter[]
The PII filters to apply to the guardrail.
readonlyoptionalregexFilters:RegexFilter[]
The regular expression (regex) filters to apply to the guardrail.
readonlyoptionalwordFilters:string[]
The word filters to apply to the guardrail.