GuardrailArgs class

The set of arguments for Guardrail. The set of arguments for Guardrail.

Constructors

GuardrailArgs({Input<GuardrailAction?>? action, required Input<String> app, Input<GuardrailCodeCallback?>? codeCallback, Input<GuardrailContentFilter?>? contentFilter, Input<String?>? deletionPolicy, Input<String?>? description, required Input<String> displayName, Input<bool?>? enabled, required Input<String> guardrailId, Input<GuardrailLlmPolicy?>? llmPolicy, Input<GuardrailLlmPromptSecurity?>? llmPromptSecurity, required Input<String> location, Input<GuardrailModelSafety?>? modelSafety, Input<String?>? project})
Creates a new GuardrailArgs. action Action that is taken when a certain precondition is met. app Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122. codeCallback Guardrail that blocks the conversation based on the code callbacks contentFilter Guardrail that bans certain content from being used in the conversation. deletionPolicy Whether Terraform will be prevented from destroying the resource. Defaults to DELETE. description Description of the guardrail. displayName Display name of the guardrail. enabled Whether the guardrail is enabled. guardrailId The ID to use for the guardrail, which will become the final component of llmPolicy Guardrail that blocks the conversation if the LLM response is considered llmPromptSecurity Guardrail that blocks the conversation if the input is considered unsafe location Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122. modelSafety Model safety settings overrides. When this is set, it will override the project The ID of the project in which the resource belongs.
const
GuardrailArgs.fromMap(Map<String, dynamic> map)
factory

Properties

action → Input<GuardrailAction?>?
Action that is taken when a certain precondition is met. Structure is documented below.
final
app → Input<String>
Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122.
final
codeCallback → Input<GuardrailCodeCallback?>?
Guardrail that blocks the conversation based on the code callbacks provided. Structure is documented below.
final
contentFilter → Input<GuardrailContentFilter?>?
Guardrail that bans certain content from being used in the conversation. Structure is documented below.
final
deletionPolicy → Input<String?>?
Whether Terraform will be prevented from destroying the resource. Defaults to DELETE. When a 'terraform destroy' or 'pulumi up' would delete the resource, the command will fail if this field is set to "PREVENT" in Terraform state. When set to "ABANDON", the command will remove the resource from Terraform management without updating or deleting the resource in the API. When set to "DELETE", deleting the resource is allowed.
final
description → Input<String?>?
Description of the guardrail.
final
displayName → Input<String>
Display name of the guardrail.
final
enabled → Input<bool?>?
Whether the guardrail is enabled.
final
guardrailId → Input<String>
The ID to use for the guardrail, which will become the final component of the guardrail's resource name. If not provided, a unique ID will be automatically assigned for the guardrail.
final
hashCode → int
The hash code for this object.
no setterinherited
llmPolicy → Input<GuardrailLlmPolicy?>?
Guardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification. Structure is documented below.
final
llmPromptSecurity → Input<GuardrailLlmPromptSecurity?>?
Guardrail that blocks the conversation if the input is considered unsafe based on the LLM classification. Structure is documented below.
final
location → Input<String>
Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122.
final
modelSafety → Input<GuardrailModelSafety?>?
Model safety settings overrides. When this is set, it will override the default settings and trigger the guardrail if the response is considered unsafe. Structure is documented below.
final
project → Input<String?>?
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toMap() → Map<String, dynamic>
toString() → String
A string representation of this object.
inherited

Operators

operator ==(Object other) → bool
The equality operator.
inherited