CfnGuardrailPropsMixin

class aws_cdk.mixins_preview.aws_bedrock.mixins.CfnGuardrailPropsMixin(props, *, strategy=None)

Bases: Mixin

Creates a guardrail to detect and filter harmful content in your generative AI application.

Amazon Bedrock Guardrails provides the following safeguards (also known as policies) to detect and filter harmful content:

  • Content filters - Detect and filter harmful text or image content in input prompts or model responses. Filtering is done based on detection of certain predefined harmful content categories: Hate, Insults, Sexual, Violence, Misconduct and Prompt Attack. You also can adjust the filter strength for each of these categories.

  • Denied topics - Define a set of topics that are undesirable in the context of your application. The filter will help block them if detected in user queries or model responses.

  • Word filters - Configure filters to help block undesirable words, phrases, and profanity (exact match). Such words can include offensive terms, competitor names, etc.

  • Sensitive information filters - Configure filters to help block or mask sensitive information, such as personally identifiable information (PII), or custom regex in user inputs and model responses. Blocking or masking is done based on probabilistic detection of sensitive information in standard formats in entities such as SSN number, Date of Birth, address, etc. This also allows configuring regular expression based detection of patterns for identifiers.

  • Contextual grounding check - Help detect and filter hallucinations in model responses based on grounding in a source and relevance to the user query.

For more information, see How Amazon Bedrock Guardrails works .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-bedrock-guardrail.html

CloudformationResource:

AWS::Bedrock::Guardrail

Mixin:

true

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview import mixins
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

cfn_guardrail_props_mixin = bedrock_mixins.CfnGuardrailPropsMixin(bedrock_mixins.CfnGuardrailMixinProps(
    automated_reasoning_policy_config=bedrock_mixins.CfnGuardrailPropsMixin.AutomatedReasoningPolicyConfigProperty(
        confidence_threshold=123,
        policies=["policies"]
    ),
    blocked_input_messaging="blockedInputMessaging",
    blocked_outputs_messaging="blockedOutputsMessaging",
    content_policy_config=bedrock_mixins.CfnGuardrailPropsMixin.ContentPolicyConfigProperty(
        content_filters_tier_config=bedrock_mixins.CfnGuardrailPropsMixin.ContentFiltersTierConfigProperty(
            tier_name="tierName"
        ),
        filters_config=[bedrock_mixins.CfnGuardrailPropsMixin.ContentFilterConfigProperty(
            input_action="inputAction",
            input_enabled=False,
            input_modalities=["inputModalities"],
            input_strength="inputStrength",
            output_action="outputAction",
            output_enabled=False,
            output_modalities=["outputModalities"],
            output_strength="outputStrength",
            type="type"
        )]
    ),
    contextual_grounding_policy_config=bedrock_mixins.CfnGuardrailPropsMixin.ContextualGroundingPolicyConfigProperty(
        filters_config=[bedrock_mixins.CfnGuardrailPropsMixin.ContextualGroundingFilterConfigProperty(
            action="action",
            enabled=False,
            threshold=123,
            type="type"
        )]
    ),
    cross_region_config=bedrock_mixins.CfnGuardrailPropsMixin.GuardrailCrossRegionConfigProperty(
        guardrail_profile_arn="guardrailProfileArn"
    ),
    description="description",
    kms_key_arn="kmsKeyArn",
    name="name",
    sensitive_information_policy_config=bedrock_mixins.CfnGuardrailPropsMixin.SensitiveInformationPolicyConfigProperty(
        pii_entities_config=[bedrock_mixins.CfnGuardrailPropsMixin.PiiEntityConfigProperty(
            action="action",
            input_action="inputAction",
            input_enabled=False,
            output_action="outputAction",
            output_enabled=False,
            type="type"
        )],
        regexes_config=[bedrock_mixins.CfnGuardrailPropsMixin.RegexConfigProperty(
            action="action",
            description="description",
            input_action="inputAction",
            input_enabled=False,
            name="name",
            output_action="outputAction",
            output_enabled=False,
            pattern="pattern"
        )]
    ),
    tags=[CfnTag(
        key="key",
        value="value"
    )],
    topic_policy_config=bedrock_mixins.CfnGuardrailPropsMixin.TopicPolicyConfigProperty(
        topics_config=[bedrock_mixins.CfnGuardrailPropsMixin.TopicConfigProperty(
            definition="definition",
            examples=["examples"],
            input_action="inputAction",
            input_enabled=False,
            name="name",
            output_action="outputAction",
            output_enabled=False,
            type="type"
        )],
        topics_tier_config=bedrock_mixins.CfnGuardrailPropsMixin.TopicsTierConfigProperty(
            tier_name="tierName"
        )
    ),
    word_policy_config=bedrock_mixins.CfnGuardrailPropsMixin.WordPolicyConfigProperty(
        managed_word_lists_config=[bedrock_mixins.CfnGuardrailPropsMixin.ManagedWordsConfigProperty(
            input_action="inputAction",
            input_enabled=False,
            output_action="outputAction",
            output_enabled=False,
            type="type"
        )],
        words_config=[bedrock_mixins.CfnGuardrailPropsMixin.WordConfigProperty(
            input_action="inputAction",
            input_enabled=False,
            output_action="outputAction",
            output_enabled=False,
            text="text"
        )]
    )
),
    strategy=mixins.PropertyMergeStrategy.OVERRIDE
)

Create a mixin to apply properties to AWS::Bedrock::Guardrail.

Parameters:

  • props (Union[CfnGuardrailMixinProps, Dict[str, Any]]) – L1 properties to apply.

  • strategy (Optional[PropertyMergeStrategy]) – (experimental) Strategy for merging nested properties. Default: - PropertyMergeStrategy.MERGE

Methods

apply_to(construct)

Apply the mixin properties to the construct.

Parameters:

construct (IConstruct)

Return type:

IConstruct

supports(construct)

Check if this mixin supports the given construct.

Parameters:

construct (IConstruct)

Return type:

bool

Attributes

CFN_PROPERTY_KEYS = ['automatedReasoningPolicyConfig', 'blockedInputMessaging', 'blockedOutputsMessaging', 'contentPolicyConfig', 'contextualGroundingPolicyConfig', 'crossRegionConfig', 'description', 'kmsKeyArn', 'name', 'sensitiveInformationPolicyConfig', 'tags', 'topicPolicyConfig', 'wordPolicyConfig']

Static Methods

classmethod is_mixin(x)

(experimental) Checks if x is a Mixin.

Parameters:

x (Any) – Any object.

Return type:

bool

Returns:

true if x is an object created from a class which extends Mixin.

Stability:

experimental

AutomatedReasoningPolicyConfigProperty

class CfnGuardrailPropsMixin.AutomatedReasoningPolicyConfigProperty(*, confidence_threshold=None, policies=None)

Bases: object

Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.

Parameters:

  • confidence_threshold (Union[int, float, None]) – The minimum confidence level required for Automated Reasoning policy violations to trigger guardrail actions. Values range from 0.0 to 1.0.

  • policies (Optional[Sequence[str]]) – The list of Automated Reasoning policy ARNs that should be applied as part of this guardrail configuration.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-automatedreasoningpolicyconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

automated_reasoning_policy_config_property = bedrock_mixins.CfnGuardrailPropsMixin.AutomatedReasoningPolicyConfigProperty(
    confidence_threshold=123,
    policies=["policies"]
)

Attributes

confidence_threshold

The minimum confidence level required for Automated Reasoning policy violations to trigger guardrail actions.

Values range from 0.0 to 1.0.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-automatedreasoningpolicyconfig.html#cfn-bedrock-guardrail-automatedreasoningpolicyconfig-confidencethreshold

policies

The list of Automated Reasoning policy ARNs that should be applied as part of this guardrail configuration.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-automatedreasoningpolicyconfig.html#cfn-bedrock-guardrail-automatedreasoningpolicyconfig-policies

ContentFilterConfigProperty

class CfnGuardrailPropsMixin.ContentFilterConfigProperty(*, input_action=None, input_enabled=None, input_modalities=None, input_strength=None, output_action=None, output_enabled=None, output_modalities=None, output_strength=None, type=None)

Bases: object

Contains filter strengths for harmful content.

Guardrails support the following content filters to detect and filter harmful user inputs and FM-generated outputs.

  • Hate – Describes language or a statement that discriminates, criticizes, insults, denounces, or dehumanizes a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).

  • Insults – Describes language or a statement that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.

  • Sexual – Describes language or a statement that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.

  • Violence – Describes language or a statement that includes glorification of or threats to inflict physical pain, hurt, or injury toward a person, group or thing.

Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.

For more information, see Guardrails content filters .

Parameters:

  • input_action (Optional[str]) – Specifies the action to take when harmful content is detected. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • input_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • input_modalities (Optional[Sequence[str]]) – The input modalities selected for the guardrail content filter configuration.

  • input_strength (Optional[str]) – The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

  • output_action (Optional[str]) – Specifies the action to take when harmful content is detected in the output. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • output_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • output_modalities (Optional[Sequence[str]]) – The output modalities selected for the guardrail content filter configuration.

  • output_strength (Optional[str]) – The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

  • type (Optional[str]) – The harmful category that the content filter is applied to.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

content_filter_config_property = bedrock_mixins.CfnGuardrailPropsMixin.ContentFilterConfigProperty(
    input_action="inputAction",
    input_enabled=False,
    input_modalities=["inputModalities"],
    input_strength="inputStrength",
    output_action="outputAction",
    output_enabled=False,
    output_modalities=["outputModalities"],
    output_strength="outputStrength",
    type="type"
)

Attributes

input_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-inputaction

Type:

Specifies the action to take when harmful content is detected. Supported values include

input_enabled

Specifies whether to enable guardrail evaluation on the input.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-inputenabled

input_modalities

The input modalities selected for the guardrail content filter configuration.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-inputmodalities

input_strength

The strength of the content filter to apply to prompts.

As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-inputstrength

output_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-outputaction

Type:

Specifies the action to take when harmful content is detected in the output. Supported values include

output_enabled

Specifies whether to enable guardrail evaluation on the output.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-outputenabled

output_modalities

The output modalities selected for the guardrail content filter configuration.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-outputmodalities

output_strength

The strength of the content filter to apply to model responses.

As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-outputstrength

type

The harmful category that the content filter is applied to.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterconfig.html#cfn-bedrock-guardrail-contentfilterconfig-type

ContentFiltersTierConfigProperty

class CfnGuardrailPropsMixin.ContentFiltersTierConfigProperty(*, tier_name=None)

Bases: object

The tier that your guardrail uses for content filters.

Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

Parameters:

tier_name (Optional[str]) – The tier that your guardrail uses for content filters. Valid values include:. - CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages. - STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterstierconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

content_filters_tier_config_property = bedrock_mixins.CfnGuardrailPropsMixin.ContentFiltersTierConfigProperty(
    tier_name="tierName"
)

Attributes

tier_name

.

  • CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.

  • STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentfilterstierconfig.html#cfn-bedrock-guardrail-contentfilterstierconfig-tiername

Type:

The tier that your guardrail uses for content filters. Valid values include

ContentPolicyConfigProperty

class CfnGuardrailPropsMixin.ContentPolicyConfigProperty(*, content_filters_tier_config=None, filters_config=None)

Bases: object

Contains details about how to handle harmful content.

Parameters:

  • content_filters_tier_config (Union[IResolvable, ContentFiltersTierConfigProperty, Dict[str, Any], None]) – The tier that your guardrail uses for content filters. Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

  • filters_config (Union[IResolvable, Sequence[Union[IResolvable, ContentFilterConfigProperty, Dict[str, Any]]], None]) – Contains the type of the content filter and how strongly it should apply to prompts and model responses.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentpolicyconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

content_policy_config_property = bedrock_mixins.CfnGuardrailPropsMixin.ContentPolicyConfigProperty(
    content_filters_tier_config=bedrock_mixins.CfnGuardrailPropsMixin.ContentFiltersTierConfigProperty(
        tier_name="tierName"
    ),
    filters_config=[bedrock_mixins.CfnGuardrailPropsMixin.ContentFilterConfigProperty(
        input_action="inputAction",
        input_enabled=False,
        input_modalities=["inputModalities"],
        input_strength="inputStrength",
        output_action="outputAction",
        output_enabled=False,
        output_modalities=["outputModalities"],
        output_strength="outputStrength",
        type="type"
    )]
)

Attributes

content_filters_tier_config

The tier that your guardrail uses for content filters.

Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentpolicyconfig.html#cfn-bedrock-guardrail-contentpolicyconfig-contentfilterstierconfig

filters_config

Contains the type of the content filter and how strongly it should apply to prompts and model responses.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contentpolicyconfig.html#cfn-bedrock-guardrail-contentpolicyconfig-filtersconfig

ContextualGroundingFilterConfigProperty

class CfnGuardrailPropsMixin.ContextualGroundingFilterConfigProperty(*, action=None, enabled=None, threshold=None, type=None)

Bases: object

The filter configuration details for the guardrails contextual grounding filter.

Parameters:

  • action (Optional[str]) – Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • enabled (Union[bool, IResolvable, None]) – Specifies whether to enable contextual grounding evaluation. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • threshold (Union[int, float, None]) – The threshold details for the guardrails contextual grounding filter.

  • type (Optional[str]) – The filter details for the guardrails contextual grounding filter.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

contextual_grounding_filter_config_property = bedrock_mixins.CfnGuardrailPropsMixin.ContextualGroundingFilterConfigProperty(
    action="action",
    enabled=False,
    threshold=123,
    type="type"
)

Attributes

action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.html#cfn-bedrock-guardrail-contextualgroundingfilterconfig-action

Type:

Specifies the action to take when content fails the contextual grounding evaluation. Supported values include

enabled

Specifies whether to enable contextual grounding evaluation.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.html#cfn-bedrock-guardrail-contextualgroundingfilterconfig-enabled

threshold

The threshold details for the guardrails contextual grounding filter.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.html#cfn-bedrock-guardrail-contextualgroundingfilterconfig-threshold

type

The filter details for the guardrails contextual grounding filter.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.html#cfn-bedrock-guardrail-contextualgroundingfilterconfig-type

ContextualGroundingPolicyConfigProperty

class CfnGuardrailPropsMixin.ContextualGroundingPolicyConfigProperty(*, filters_config=None)

Bases: object

The policy configuration details for the guardrails contextual grounding policy.

Parameters:

filters_config (Union[IResolvable, Sequence[Union[IResolvable, ContextualGroundingFilterConfigProperty, Dict[str, Any]]], None]) – List of contextual grounding filter configs.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingpolicyconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

contextual_grounding_policy_config_property = bedrock_mixins.CfnGuardrailPropsMixin.ContextualGroundingPolicyConfigProperty(
    filters_config=[bedrock_mixins.CfnGuardrailPropsMixin.ContextualGroundingFilterConfigProperty(
        action="action",
        enabled=False,
        threshold=123,
        type="type"
    )]
)

Attributes

filters_config

List of contextual grounding filter configs.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-contextualgroundingpolicyconfig.html#cfn-bedrock-guardrail-contextualgroundingpolicyconfig-filtersconfig

GuardrailCrossRegionConfigProperty

class CfnGuardrailPropsMixin.GuardrailCrossRegionConfigProperty(*, guardrail_profile_arn=None)

Bases: object

The system-defined guardrail profile that you’re using with your guardrail.

Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

For more information, see the Amazon Bedrock User Guide .

Parameters:

guardrail_profile_arn (Optional[str]) –

The Amazon Resource Name (ARN) of the guardrail profile that your guardrail is using. Guardrail profile availability depends on your current AWS Region . For more information, see the Amazon Bedrock User Guide .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-guardrailcrossregionconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

guardrail_cross_region_config_property = bedrock_mixins.CfnGuardrailPropsMixin.GuardrailCrossRegionConfigProperty(
    guardrail_profile_arn="guardrailProfileArn"
)

Attributes

guardrail_profile_arn

The Amazon Resource Name (ARN) of the guardrail profile that your guardrail is using.

Guardrail profile availability depends on your current AWS Region . For more information, see the Amazon Bedrock User Guide .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-guardrailcrossregionconfig.html#cfn-bedrock-guardrail-guardrailcrossregionconfig-guardrailprofilearn

ManagedWordsConfigProperty

class CfnGuardrailPropsMixin.ManagedWordsConfigProperty(*, input_action=None, input_enabled=None, output_action=None, output_enabled=None, type=None)

Bases: object

The managed word list to configure for the guardrail.

Parameters:

  • input_action (Optional[str]) – Specifies the action to take when harmful content is detected in the input. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • input_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • output_action (Optional[str]) – Specifies the action to take when harmful content is detected in the output. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • output_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • type (Optional[str]) – The managed word type to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-managedwordsconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

managed_words_config_property = bedrock_mixins.CfnGuardrailPropsMixin.ManagedWordsConfigProperty(
    input_action="inputAction",
    input_enabled=False,
    output_action="outputAction",
    output_enabled=False,
    type="type"
)

Attributes

input_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-managedwordsconfig.html#cfn-bedrock-guardrail-managedwordsconfig-inputaction

Type:

Specifies the action to take when harmful content is detected in the input. Supported values include

input_enabled

Specifies whether to enable guardrail evaluation on the input.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-managedwordsconfig.html#cfn-bedrock-guardrail-managedwordsconfig-inputenabled

output_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-managedwordsconfig.html#cfn-bedrock-guardrail-managedwordsconfig-outputaction

Type:

Specifies the action to take when harmful content is detected in the output. Supported values include

output_enabled

Specifies whether to enable guardrail evaluation on the output.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-managedwordsconfig.html#cfn-bedrock-guardrail-managedwordsconfig-outputenabled

type

The managed word type to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-managedwordsconfig.html#cfn-bedrock-guardrail-managedwordsconfig-type

PiiEntityConfigProperty

class CfnGuardrailPropsMixin.PiiEntityConfigProperty(*, action=None, input_action=None, input_enabled=None, output_action=None, output_enabled=None, type=None)

Bases: object

The PII entity to configure for the guardrail.

Parameters:

  • action (Optional[str]) – Configure guardrail action when the PII entity is detected.

  • input_action (Optional[str]) – Specifies the action to take when harmful content is detected in the input. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - ANONYMIZE – Mask the content and replace it with identifier tags. - NONE – Take no action but return detection information in the trace response.

  • input_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • output_action (Optional[str]) – Specifies the action to take when harmful content is detected in the output. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - ANONYMIZE – Mask the content and replace it with identifier tags. - NONE – Take no action but return detection information in the trace response.

  • output_enabled (Union[bool, IResolvable, None]) – Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • type (Optional[str]) – Configure guardrail type when the PII entity is detected. The following PIIs are used to block or mask sensitive information: - General - ADDRESS A physical address, such as “100 Main Street, Anytown, USA” or “Suite #12, Building 123”. An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood. - AGE An individual’s age, including the quantity and unit of time. For example, in the phrase “I am 40 years old,” Guardrails recognizes “40 years” as an age. - NAME An individual’s name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn’t apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the “John Doe Organization” as an organization, and it recognizes “Jane Doe Street” as an address. - EMAIL An email address, such as marymajor@email.com . - PHONE A phone number. This entity type also includes fax and pager numbers. - USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle. - PASSWORD An alphanumeric string that is used as a password, such as “* very20special#pass* “. - DRIVER_ID The number assigned to a driver’s license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver’s license number consists of alphanumeric characters. - LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country. - VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs. - Finance - CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code. - CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 . - CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present. - PIN A four-digit personal identification number (PIN) with which you can access your bank account. - INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure . - SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in ‘XXX’) refer to the head or primary office. - IT - IP_ADDRESS An IPv4 address, such as 198.51.100.0 . - MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC). - URL A web address, such as www.example.com . - AWS_ACCESS_KEY A unique identifier that’s associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically. - AWS_SECRET_KEY A unique identifier that’s associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically. - USA specific - US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long. - US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long, - US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a “9” and contain a “7” or “8” as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits. - US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters. - US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents. - Canada specific - CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits. - CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm . - UK Specific - UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum. - UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits. - UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business. - Custom - Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

pii_entity_config_property = bedrock_mixins.CfnGuardrailPropsMixin.PiiEntityConfigProperty(
    action="action",
    input_action="inputAction",
    input_enabled=False,
    output_action="outputAction",
    output_enabled=False,
    type="type"
)

Attributes

action

Configure guardrail action when the PII entity is detected.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html#cfn-bedrock-guardrail-piientityconfig-action

input_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • ANONYMIZE – Mask the content and replace it with identifier tags.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html#cfn-bedrock-guardrail-piientityconfig-inputaction

Type:

Specifies the action to take when harmful content is detected in the input. Supported values include

input_enabled

Specifies whether to enable guardrail evaluation on the input.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html#cfn-bedrock-guardrail-piientityconfig-inputenabled

output_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • ANONYMIZE – Mask the content and replace it with identifier tags.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html#cfn-bedrock-guardrail-piientityconfig-outputaction

Type:

Specifies the action to take when harmful content is detected in the output. Supported values include

output_enabled

Indicates whether guardrail evaluation is enabled on the output.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html#cfn-bedrock-guardrail-piientityconfig-outputenabled

type

Configure guardrail type when the PII entity is detected.

The following PIIs are used to block or mask sensitive information:

  • General

  • ADDRESS

A physical address, such as “100 Main Street, Anytown, USA” or “Suite #12, Building 123”. An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

  • AGE

An individual’s age, including the quantity and unit of time. For example, in the phrase “I am 40 years old,” Guardrails recognizes “40 years” as an age.

  • NAME

An individual’s name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn’t apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the “John Doe Organization” as an organization, and it recognizes “Jane Doe Street” as an address.

  • EMAIL

An email address, such as marymajor@email.com .

  • PHONE

A phone number. This entity type also includes fax and pager numbers.

  • USERNAME

A user name that identifies an account, such as a login name, screen name, nick name, or handle.

  • PASSWORD

An alphanumeric string that is used as a password, such as “* very20special#pass* “.

  • DRIVER_ID

The number assigned to a driver’s license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver’s license number consists of alphanumeric characters.

  • LICENSE_PLATE

A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

  • VEHICLE_IDENTIFICATION_NUMBER

A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

  • Finance

  • CREDIT_DEBIT_CARD_CVV

A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

  • CREDIT_DEBIT_CARD_EXPIRY

The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

  • CREDIT_DEBIT_CARD_NUMBER

The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

  • PIN

A four-digit personal identification number (PIN) with which you can access your bank account.

  • INTERNATIONAL_BANK_ACCOUNT_NUMBER

An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

  • SWIFT_CODE

A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in ‘XXX’) refer to the head or primary office.

  • IT

  • IP_ADDRESS

An IPv4 address, such as 198.51.100.0 .

  • MAC_ADDRESS

A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

  • URL

A web address, such as www.example.com .

  • AWS_ACCESS_KEY

A unique identifier that’s associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

  • AWS_SECRET_KEY

A unique identifier that’s associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

  • USA specific

  • US_BANK_ACCOUNT_NUMBER

A US bank account number, which is typically 10 to 12 digits long.

  • US_BANK_ROUTING_NUMBER

A US bank account routing number. These are typically nine digits long,

  • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a “9” and contain a “7” or “8” as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

  • US_PASSPORT_NUMBER

A US passport number. Passport numbers range from six to nine alphanumeric characters.

  • US_SOCIAL_SECURITY_NUMBER

A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

  • Canada specific

  • CA_HEALTH_NUMBER

A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

  • CA_SOCIAL_INSURANCE_NUMBER

A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

  • UK Specific

  • UK_NATIONAL_HEALTH_SERVICE_NUMBER

A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

  • UK_NATIONAL_INSURANCE_NUMBER

A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

  • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

  • Custom

  • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-piientityconfig.html#cfn-bedrock-guardrail-piientityconfig-type

RegexConfigProperty

class CfnGuardrailPropsMixin.RegexConfigProperty(*, action=None, description=None, input_action=None, input_enabled=None, name=None, output_action=None, output_enabled=None, pattern=None)

Bases: object

The regular expression to configure for the guardrail.

Parameters:

  • action (Optional[str]) – The guardrail action to configure when matching regular expression is detected.

  • description (Optional[str]) – The description of the regular expression to configure for the guardrail.

  • input_action (Optional[str]) – Specifies the action to take when harmful content is detected in the input. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • input_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • name (Optional[str]) – The name of the regular expression to configure for the guardrail.

  • output_action (Optional[str]) – Specifies the action to take when harmful content is detected in the output. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • output_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • pattern (Optional[str]) – The regular expression pattern to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

regex_config_property = bedrock_mixins.CfnGuardrailPropsMixin.RegexConfigProperty(
    action="action",
    description="description",
    input_action="inputAction",
    input_enabled=False,
    name="name",
    output_action="outputAction",
    output_enabled=False,
    pattern="pattern"
)

Attributes

action

The guardrail action to configure when matching regular expression is detected.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-action

description

The description of the regular expression to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-description

input_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-inputaction

Type:

Specifies the action to take when harmful content is detected in the input. Supported values include

input_enabled

Specifies whether to enable guardrail evaluation on the input.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-inputenabled

name

The name of the regular expression to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-name

output_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-outputaction

Type:

Specifies the action to take when harmful content is detected in the output. Supported values include

output_enabled

Specifies whether to enable guardrail evaluation on the output.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-outputenabled

pattern

The regular expression pattern to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-regexconfig.html#cfn-bedrock-guardrail-regexconfig-pattern

SensitiveInformationPolicyConfigProperty

class CfnGuardrailPropsMixin.SensitiveInformationPolicyConfigProperty(*, pii_entities_config=None, regexes_config=None)

Bases: object

Contains details about PII entities and regular expressions to configure for the guardrail.

Parameters:
See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-sensitiveinformationpolicyconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

sensitive_information_policy_config_property = bedrock_mixins.CfnGuardrailPropsMixin.SensitiveInformationPolicyConfigProperty(
    pii_entities_config=[bedrock_mixins.CfnGuardrailPropsMixin.PiiEntityConfigProperty(
        action="action",
        input_action="inputAction",
        input_enabled=False,
        output_action="outputAction",
        output_enabled=False,
        type="type"
    )],
    regexes_config=[bedrock_mixins.CfnGuardrailPropsMixin.RegexConfigProperty(
        action="action",
        description="description",
        input_action="inputAction",
        input_enabled=False,
        name="name",
        output_action="outputAction",
        output_enabled=False,
        pattern="pattern"
    )]
)

Attributes

pii_entities_config

A list of PII entities to configure to the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-sensitiveinformationpolicyconfig.html#cfn-bedrock-guardrail-sensitiveinformationpolicyconfig-piientitiesconfig

regexes_config

A list of regular expressions to configure to the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-sensitiveinformationpolicyconfig.html#cfn-bedrock-guardrail-sensitiveinformationpolicyconfig-regexesconfig

TopicConfigProperty

class CfnGuardrailPropsMixin.TopicConfigProperty(*, definition=None, examples=None, input_action=None, input_enabled=None, name=None, output_action=None, output_enabled=None, type=None)

Bases: object

Details about topics for the guardrail to identify and deny.

Parameters:

  • definition (Optional[str]) – A definition of the topic to deny.

  • examples (Optional[Sequence[str]]) – A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.

  • input_action (Optional[str]) – Specifies the action to take when harmful content is detected in the input. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • input_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • name (Optional[str]) – The name of the topic to deny.

  • output_action (Optional[str]) – Specifies the action to take when harmful content is detected in the output. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • output_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • type (Optional[str]) – Specifies to deny the topic.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

topic_config_property = bedrock_mixins.CfnGuardrailPropsMixin.TopicConfigProperty(
    definition="definition",
    examples=["examples"],
    input_action="inputAction",
    input_enabled=False,
    name="name",
    output_action="outputAction",
    output_enabled=False,
    type="type"
)

Attributes

definition

A definition of the topic to deny.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-definition

examples

A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-examples

input_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-inputaction

Type:

Specifies the action to take when harmful content is detected in the input. Supported values include

input_enabled

Specifies whether to enable guardrail evaluation on the input.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-inputenabled

name

The name of the topic to deny.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-name

output_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-outputaction

Type:

Specifies the action to take when harmful content is detected in the output. Supported values include

output_enabled

Specifies whether to enable guardrail evaluation on the output.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-outputenabled

type

Specifies to deny the topic.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicconfig.html#cfn-bedrock-guardrail-topicconfig-type

TopicPolicyConfigProperty

class CfnGuardrailPropsMixin.TopicPolicyConfigProperty(*, topics_config=None, topics_tier_config=None)

Bases: object

Contains details about topics that the guardrail should identify and deny.

Parameters:
See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicpolicyconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

topic_policy_config_property = bedrock_mixins.CfnGuardrailPropsMixin.TopicPolicyConfigProperty(
    topics_config=[bedrock_mixins.CfnGuardrailPropsMixin.TopicConfigProperty(
        definition="definition",
        examples=["examples"],
        input_action="inputAction",
        input_enabled=False,
        name="name",
        output_action="outputAction",
        output_enabled=False,
        type="type"
    )],
    topics_tier_config=bedrock_mixins.CfnGuardrailPropsMixin.TopicsTierConfigProperty(
        tier_name="tierName"
    )
)

Attributes

topics_config

A list of policies related to topics that the guardrail should deny.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicpolicyconfig.html#cfn-bedrock-guardrail-topicpolicyconfig-topicsconfig

topics_tier_config

The tier that your guardrail uses for denied topic filters.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicpolicyconfig.html#cfn-bedrock-guardrail-topicpolicyconfig-topicstierconfig

TopicsTierConfigProperty

class CfnGuardrailPropsMixin.TopicsTierConfigProperty(*, tier_name=None)

Bases: object

The tier that your guardrail uses for denied topic filters.

Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

Parameters:

tier_name (Optional[str]) –

The tier that your guardrail uses for denied topic filters. Valid values include:. - CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages. - STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicstierconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

topics_tier_config_property = bedrock_mixins.CfnGuardrailPropsMixin.TopicsTierConfigProperty(
    tier_name="tierName"
)

Attributes

tier_name

.

  • CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.

  • STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference .

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-topicstierconfig.html#cfn-bedrock-guardrail-topicstierconfig-tiername

Type:

The tier that your guardrail uses for denied topic filters. Valid values include

WordConfigProperty

class CfnGuardrailPropsMixin.WordConfigProperty(*, input_action=None, input_enabled=None, output_action=None, output_enabled=None, text=None)

Bases: object

A word to configure for the guardrail.

Parameters:

  • input_action (Optional[str]) – Specifies the action to take when harmful content is detected in the input. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • input_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • output_action (Optional[str]) – Specifies the action to take when harmful content is detected in the output. Supported values include:. - BLOCK – Block the content and replace it with blocked messaging. - NONE – Take no action but return detection information in the trace response.

  • output_enabled (Union[bool, IResolvable, None]) – Specifies whether to enable guardrail evaluation on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

  • text (Optional[str]) – Text of the word configured for the guardrail to block.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

word_config_property = bedrock_mixins.CfnGuardrailPropsMixin.WordConfigProperty(
    input_action="inputAction",
    input_enabled=False,
    output_action="outputAction",
    output_enabled=False,
    text="text"
)

Attributes

input_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordconfig.html#cfn-bedrock-guardrail-wordconfig-inputaction

Type:

Specifies the action to take when harmful content is detected in the input. Supported values include

input_enabled

Specifies whether to enable guardrail evaluation on the intput.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordconfig.html#cfn-bedrock-guardrail-wordconfig-inputenabled

output_action

.

  • BLOCK – Block the content and replace it with blocked messaging.

  • NONE – Take no action but return detection information in the trace response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordconfig.html#cfn-bedrock-guardrail-wordconfig-outputaction

Type:

Specifies the action to take when harmful content is detected in the output. Supported values include

output_enabled

Specifies whether to enable guardrail evaluation on the output.

When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordconfig.html#cfn-bedrock-guardrail-wordconfig-outputenabled

text

Text of the word configured for the guardrail to block.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordconfig.html#cfn-bedrock-guardrail-wordconfig-text

WordPolicyConfigProperty

class CfnGuardrailPropsMixin.WordPolicyConfigProperty(*, managed_word_lists_config=None, words_config=None)

Bases: object

Contains details about the word policy to configured for the guardrail.

Parameters:
See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordpolicyconfig.html

ExampleMetadata:

fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk.mixins_preview.aws_bedrock import mixins as bedrock_mixins

word_policy_config_property = bedrock_mixins.CfnGuardrailPropsMixin.WordPolicyConfigProperty(
    managed_word_lists_config=[bedrock_mixins.CfnGuardrailPropsMixin.ManagedWordsConfigProperty(
        input_action="inputAction",
        input_enabled=False,
        output_action="outputAction",
        output_enabled=False,
        type="type"
    )],
    words_config=[bedrock_mixins.CfnGuardrailPropsMixin.WordConfigProperty(
        input_action="inputAction",
        input_enabled=False,
        output_action="outputAction",
        output_enabled=False,
        text="text"
    )]
)

Attributes

managed_word_lists_config

A list of managed words to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordpolicyconfig.html#cfn-bedrock-guardrail-wordpolicyconfig-managedwordlistsconfig

words_config

A list of words to configure for the guardrail.

See:

http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-bedrock-guardrail-wordpolicyconfig.html#cfn-bedrock-guardrail-wordpolicyconfig-wordsconfig