CreateGuardrailRequest ¶

class CreateGuardrailRequest(TypedDict, closed=True):
    name: "capo_bedrock.types.guardrail_name.GuardrailName"
    """<p>The name to give the guardrail.</p>"""
    description: NotRequired[
        "capo_bedrock.types.guardrail_description.GuardrailDescription"
    ]
    """<p>A description of the guardrail.</p>"""
    topic_policy_config: NotRequired[
        "capo_bedrock.types.guardrail_topic_policy_config.GuardrailTopicPolicyConfig"
    ]
    """<p>The topic policies to configure for the guardrail.</p>"""
    content_policy_config: NotRequired[
        "capo_bedrock.types.guardrail_content_policy_config.GuardrailContentPolicyConfig"
    ]
    """<p>The content filter policies to configure for the guardrail.</p>"""
    word_policy_config: NotRequired[
        "capo_bedrock.types.guardrail_word_policy_config.GuardrailWordPolicyConfig"
    ]
    """<p>The word policy you configure for the guardrail.</p>"""
    sensitive_information_policy_config: NotRequired[
        "capo_bedrock.types.guardrail_sensitive_information_policy_config.GuardrailSensitiveInformationPolicyConfig"
    ]
    """<p>The sensitive information policy to configure for the guardrail.</p>"""
    contextual_grounding_policy_config: NotRequired[
        "capo_bedrock.types.guardrail_contextual_grounding_policy_config.GuardrailContextualGroundingPolicyConfig"
    ]
    """<p>The contextual grounding policy configuration used to create a guardrail.</p>"""
    automated_reasoning_policy_config: NotRequired[
        "capo_bedrock.types.guardrail_automated_reasoning_policy_config.GuardrailAutomatedReasoningPolicyConfig"
    ]
    """<p>Optional configuration for integrating Automated Reasoning policies with the new guardrail.</p>"""
    cross_region_config: NotRequired[
        "capo_bedrock.types.guardrail_cross_region_config.GuardrailCrossRegionConfig"
    ]
    """<p>The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed.</p> <p>For more information, see the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region.html">Amazon Bedrock User Guide</a>.</p>"""
    blocked_input_messaging: (
        "capo_bedrock.types.guardrail_blocked_messaging.GuardrailBlockedMessaging"
    )
    """<p>The message to return when the guardrail blocks a prompt.</p>"""
    blocked_outputs_messaging: (
        "capo_bedrock.types.guardrail_blocked_messaging.GuardrailBlockedMessaging"
    )
    """<p>The message to return when the guardrail blocks a model response.</p>"""
    kms_key_id: NotRequired["capo_bedrock.types.kms_key_id.KmsKeyId"]
    """<p>The ARN of the KMS key that you use to encrypt the guardrail.</p>"""
    tags: NotRequired["capo_bedrock.types.tag_list.TagList"]
    """<p>The tags that you want to attach to the guardrail. </p>"""
    client_request_token: NotRequired[
        "capo_bedrock.types.idempotency_token.IdempotencyToken"
    ]
    """<p>A unique, case-sensitive identifier to ensure that the API request completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see <a href="https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a> in the <i>Amazon S3 User Guide</i>.</p>"""