Values.GuardrailTopicConfigSourceDetails about topics for the guardrail to identify and deny.
type nonrec t = {name : GuardrailTopicName.t;The name of the topic to deny.
*)definition : GuardrailTopicDefinition.t;A definition of the topic to deny.
*)examples : GuardrailTopicExamples.t option;A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
*)type_ : GuardrailTopicType.t;Specifies to deny the topic.
*)inputAction : GuardrailTopicAction.t option;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.
*)outputAction : GuardrailTopicAction.t option;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.
*)inputEnabled : Boolean.t option;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.
*)outputEnabled : Boolean.t option;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.
*)}val make :
?examples:??? ->
?inputAction:??? ->
?outputAction:??? ->
?inputEnabled:??? ->
?outputEnabled:??? ->
name:GuardrailTopicName.t ->
definition:GuardrailTopicDefinition.t ->
type_:GuardrailTopicType.t ->
unit ->
tval to_value :
t ->
[> `Structure of
(string
* [> `Boolean of Boolean.t
| `Enum of string
| `List of [> `String of GuardrailTopicExample.t ] list
| `String of GuardrailTopicName.t ])
list ]