Gemini Enterprise for Customer Experience V1 API - Class Google::Cloud::Ces::V1::Guardrail::LlmPolicy (v0.1.0)

Reference documentation and code samples for the Gemini Enterprise for Customer Experience V1 API class Google::Cloud::Ces::V1::Guardrail::LlmPolicy.

Guardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#allow_short_utterance

def allow_short_utterance() -> ::Boolean
Returns
  • (::Boolean) — Optional. 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.

#allow_short_utterance=

def allow_short_utterance=(value) -> ::Boolean
Parameter
  • value (::Boolean) — Optional. 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.
Returns
  • (::Boolean) — Optional. 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.

#fail_open

def fail_open() -> ::Boolean
Returns
  • (::Boolean) — Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.

#fail_open=

def fail_open=(value) -> ::Boolean
Parameter
  • value (::Boolean) — Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.
Returns
  • (::Boolean) — Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.

#max_conversation_messages

def max_conversation_messages() -> ::Integer
Returns
  • (::Integer) — Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.

#max_conversation_messages=

def max_conversation_messages=(value) -> ::Integer
Parameter
  • value (::Integer) — Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.
Returns
  • (::Integer) — Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.

#model_settings

def model_settings() -> ::Google::Cloud::Ces::V1::ModelSettings
Returns

#model_settings=

def model_settings=(value) -> ::Google::Cloud::Ces::V1::ModelSettings
Parameter
Returns

#policy_scope

def policy_scope() -> ::Google::Cloud::Ces::V1::Guardrail::LlmPolicy::PolicyScope
Returns
  • (::Google::Cloud::Ces::V1::Guardrail::LlmPolicy::PolicyScope) — Required. 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.

#policy_scope=

def policy_scope=(value) -> ::Google::Cloud::Ces::V1::Guardrail::LlmPolicy::PolicyScope
Parameter
  • value (::Google::Cloud::Ces::V1::Guardrail::LlmPolicy::PolicyScope) — Required. 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.
Returns
  • (::Google::Cloud::Ces::V1::Guardrail::LlmPolicy::PolicyScope) — Required. 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.

#prompt

def prompt() -> ::String
Returns
  • (::String) — Required. Policy prompt.

#prompt=

def prompt=(value) -> ::String
Parameter
  • value (::String) — Required. Policy prompt.
Returns
  • (::String) — Required. Policy prompt.