Module Values.CreateGuardrailResponseSource

Creates a guardrail to block topics and to implement safeguards for your generative AI applications. You can configure the following policies in a guardrail to avoid undesirable and harmful content, filter out denied topics and words, and remove sensitive information for privacy protection. Content filters - Adjust filter strengths to block input prompts or model responses containing harmful content. Denied topics - Define a set of topics that are undesirable in the context of your application. These topics will be blocked if detected in user queries or model responses. Word filters - Configure filters to block undesirable words, phrases, and profanity. Such words can include offensive terms, competitor names etc. Sensitive information filters - Block or mask sensitive information such as personally identifiable information (PII) or custom regex in user inputs and model responses. In addition to the above policies, you can also configure the messages to be returned to the user if a user input or model response is in violation of the policies defined in the guardrail. For more information, see Amazon Bedrock Guardrails in the Amazon Bedrock User Guide.

Sourcetype nonrec t = {
  1. guardrailId : GuardrailId.t option;
    (*

    The unique identifier of the guardrail that was created.

    *)
  2. guardrailArn : GuardrailArn.t option;
    (*

    The ARN of the guardrail.

    *)
  3. version : GuardrailDraftVersion.t option;
    (*

    The version of the guardrail that was created. This value will always be DRAFT.

    *)
  4. createdAt : Timestamp.t option;
    (*

    The time at which the guardrail was created.

    *)
}
Sourcetype nonrec error = [
  1. | `AccessDeniedException of AccessDeniedException.t
  2. | `ConflictException of ConflictException.t
  3. | `InternalServerException of InternalServerException.t
  4. | `ResourceNotFoundException of ResourceNotFoundException.t
  5. | `ServiceQuotaExceededException of ServiceQuotaExceededException.t
  6. | `ThrottlingException of ThrottlingException.t
  7. | `TooManyTagsException of TooManyTagsException.t
  8. | `ValidationException of ValidationException.t
  9. | `Unknown_operation_error of string * string option
]
Sourceval make : ?guardrailId:??? -> ?guardrailArn:??? -> ?version:??? -> ?createdAt:??? -> unit -> t
Sourceval error_of_json : string -> Yojson.Safe.t -> [> `AccessDeniedException of AccessDeniedException.t | `ConflictException of ConflictException.t | `InternalServerException of InternalServerException.t | `ResourceNotFoundException of ResourceNotFoundException.t | `ServiceQuotaExceededException of ServiceQuotaExceededException.t | `ThrottlingException of ThrottlingException.t | `TooManyTagsException of TooManyTagsException.t | `Unknown_operation_error of string * string option | `ValidationException of ValidationException.t ]
Sourceval error_of_xml : string -> Awso.Xml.t -> [> `AccessDeniedException of AccessDeniedException.t | `ConflictException of ConflictException.t | `InternalServerException of InternalServerException.t | `ResourceNotFoundException of ResourceNotFoundException.t | `ServiceQuotaExceededException of ServiceQuotaExceededException.t | `ThrottlingException of ThrottlingException.t | `TooManyTagsException of TooManyTagsException.t | `Unknown_operation_error of string * string option | `ValidationException of ValidationException.t ]
Sourceval error_to_json : error -> Yojson.Safe.t
Sourceval to_value : t -> [> `Structure of (string * [> `String of GuardrailId.t | `Timestamp of Timestamp.t ]) list ]
Sourceval to_query : t -> Awso.Client.Query.t
Sourceval of_xml : Awso.Xml.t -> t
Sourceval of_string : string -> t
Sourceval of_json : Yojson.Safe.t -> t
Sourceval to_json : t -> Yojson.Safe.t