Experimental
@aws-cdk/aws-bedrock-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.
GuardrailProps Struct
Properties for creating a Guardrail.
Example
ts
const guardrail = new bedrock.Guardrail(this, 'bedrockGuardrails', {
guardrailName: 'my-BedrockGuardrails',
});
// Add regex filter with input/output actions
guardrail.addRegexFilter({
name: 'TestRegexFilter',
pattern: 'test-pattern',
action: bedrock.GuardrailAction.ANONYMIZE,
// below props are optional
description: 'This is a test regex filter',
inputAction: bedrock.GuardrailAction.BLOCK,
inputEnabled: true,
outputAction: bedrock.GuardrailAction.ANONYMIZE,
outputEnabled: true,
});
Properties
blockedInputMessagingoptionalstringblocked_input_messagingoptionalstrblockedInputMessagingoptionalStringBlockedInputMessagingoptionalstringBlockedInputMessagingoptional*string#The message to return when the guardrail blocks a prompt.
Default: "Sorry, your query violates our usage policy."
Must be between 1 and 500 characters.
blockedOutputsMessagingoptionalstringblocked_outputs_messagingoptionalstrblockedOutputsMessagingoptionalStringBlockedOutputsMessagingoptionalstringBlockedOutputsMessagingoptional*string#The message to return when the guardrail blocks a model response.
Default: "Sorry, I am unable to answer your question because of our usage policy."
Must be between 1 and 500 characters.
contentFiltersoptionalContentFilter[]content_filtersoptionaltyping.List[ContentFilter]contentFiltersoptionalList<ContentFilter>ContentFiltersoptionalContentFilter[]ContentFiltersoptional*[]ContentFilter= []#The content filters to apply to the guardrail.
contentFiltersTierConfigoptionalTierConfigcontent_filters_tier_configoptionalTierConfigcontentFiltersTierConfigoptionalTierConfigContentFiltersTierConfigoptionalTierConfigContentFiltersTierConfigoptionalTierConfig= filters.TierConfig.CLASSIC#The tier configuration to apply to the guardrail.
contextualGroundingFiltersoptionalContextualGroundingFilter[]contextual_grounding_filtersoptionaltyping.List[ContextualGroundingFilter]contextualGroundingFiltersoptionalList<ContextualGroundingFilter>ContextualGroundingFiltersoptionalContextualGroundingFilter[]ContextualGroundingFiltersoptional*[]ContextualGroundingFilter= []#The contextual grounding filters to apply to the guardrail.
crossRegionConfigoptionalGuardrailCrossRegionConfigPropertycross_region_configoptionalGuardrailCrossRegionConfigPropertycrossRegionConfigoptionalGuardrailCrossRegionConfigPropertyCrossRegionConfigoptionalGuardrailCrossRegionConfigPropertyCrossRegionConfigoptionalGuardrailCrossRegionConfigProperty#The cross-region configuration for the guardrail.
Default: No cross-region configuration
This is optional and when provided, it should be of type GuardrailCrossRegionConfigProperty.
deniedTopicsoptionalTopic[]denied_topicsoptionaltyping.List[Topic]deniedTopicsoptionalList<Topic>DeniedTopicsoptionalTopic[]DeniedTopicsoptional*[]Topic= []#A list of policies related to topics that the guardrail should deny.
descriptionoptionalstringdescriptionoptionalstrdescriptionoptionalStringDescriptionoptionalstringDescriptionoptional*string#The description of the guardrail.
Default: No description
guardrailNamestringguardrail_namestrguardrailNameStringGuardrailNamestringGuardrailName*stringrequired#The name of the guardrail.
This will be used as the physical name of the guardrail.
A custom KMS key to use for encrypting data.
Default: Data is encrypted by default with a key that AWS owns and manages for you
managedWordListFiltersoptionalManagedWordFilter[]managed_word_list_filtersoptionaltyping.List[ManagedWordFilter]managedWordListFiltersoptionalList<ManagedWordFilter>ManagedWordListFiltersoptionalManagedWordFilter[]ManagedWordListFiltersoptional*[]ManagedWordFilter= []#The managed word filters to apply to the guardrail.
piiFiltersoptionalPIIFilter[]pii_filtersoptionaltyping.List[PIIFilter]piiFiltersoptionalList<PIIFilter>PiiFiltersoptionalPIIFilter[]PiiFiltersoptional*[]PIIFilter= []#The PII filters to apply to the guardrail.
regexFiltersoptionalRegexFilter[]regex_filtersoptionaltyping.List[RegexFilter]regexFiltersoptionalList<RegexFilter>RegexFiltersoptionalRegexFilter[]RegexFiltersoptional*[]RegexFilter= []#The regular expression (regex) filters to apply to the guardrail.
topicsTierConfigoptionalTierConfigtopics_tier_configoptionalTierConfigtopicsTierConfigoptionalTierConfigTopicsTierConfigoptionalTierConfigTopicsTierConfigoptionalTierConfig= filters.TierConfig.CLASSIC#The tier configuration to apply to the guardrail.
wordFiltersoptionalWordFilter[]word_filtersoptionaltyping.List[WordFilter]wordFiltersoptionalList<WordFilter>WordFiltersoptionalWordFilter[]WordFiltersoptional*[]WordFilter= []#The word filters to apply to the guardrail.