GuardrailLlmPromptSecurityCustomPolicy class

Constructors

GuardrailLlmPromptSecurityCustomPolicy({Input<bool?>? allowShortUtterance, Input<bool?>? failOpen, Input<int?>? maxConversationMessages, Input<GuardrailLlmPromptSecurityCustomPolicyModelSettings?>? modelSettings, required Input<String> policyScope, required Input<String> prompt})
Creates a new GuardrailLlmPromptSecurityCustomPolicy. allowShortUtterance By default, the LLM policy check is bypassed for short utterances. failOpen If an error occurs during the policy check, fail open and do not trigger maxConversationMessages When checking this policy, consider the last 'n' messages in the modelSettings Model settings contains various configurations for the LLM model. policyScope Defines when to apply the policy check during the conversation. If set to prompt Policy prompt.
const
GuardrailLlmPromptSecurityCustomPolicy.fromMap(Map<String, dynamic> map)
factory

Properties

allowShortUtterance → Input<bool?>?
By default, the LLM policy check is bypassed for short utterances. Enabling this setting applies the policy check to all utterances, including those that would normally be skipped.
final
failOpen → Input<bool?>?
If an error occurs during the policy check, fail open and do not trigger the guardrail.
final
hashCode → int
The hash code for this object.
no setterinherited
maxConversationMessages → Input<int?>?
When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.
final
modelSettings → Input<GuardrailLlmPromptSecurityCustomPolicyModelSettings?>?
Model settings contains various configurations for the LLM model. Structure is documented below.
final
policyScope → Input<String>
Defines when to apply the policy check during the conversation. If set to POLICY_SCOPE_UNSPECIFIED, the policy will be applied to the user input. When applying the policy to the agent response, additional latency will be introduced before the agent can respond. Possible values: USER_QUERY AGENT_RESPONSE USER_QUERY_AND_AGENT_RESPONSE
final
prompt → Input<String>
Policy prompt.
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