Class: Google::Apis::CesV1::GuardrailLlmPolicy

Inherits:
Object
  • Object
show all
Includes:
Google::Apis::Core::Hashable, Google::Apis::Core::JsonObjectSupport
Defined in:
lib/google/apis/ces_v1/classes.rb,
lib/google/apis/ces_v1/representations.rb,
lib/google/apis/ces_v1/representations.rb

Overview

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

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GuardrailLlmPolicy

Returns a new instance of GuardrailLlmPolicy.



4047
4048
4049
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4047

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#allow_short_utterance ⇒ Boolean Also known as: allow_short_utterance?

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. Corresponds to the JSON property allowShortUtterance

Returns:

  • (Boolean) 


4013
4014
4015
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4013

def allow_short_utterance
  @allow_short_utterance
end

#fail_open ⇒ Boolean Also known as: fail_open?

Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail. Corresponds to the JSON property failOpen

Returns:

  • (Boolean) 


4020
4021
4022
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4020

def fail_open
  @fail_open
end

#max_conversation_messages ⇒ Fixnum

Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used. Corresponds to the JSON property maxConversationMessages

Returns:

  • (Fixnum) 


4027
4028
4029
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4027

def max_conversation_messages
  @max_conversation_messages
end

#model_settings ⇒ Google::Apis::CesV1::ModelSettings

Model settings contains various configurations for the LLM model. Corresponds to the JSON property modelSettings

Returns:



4032
4033
4034
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4032

def model_settings
  @model_settings
end

#policy_scope ⇒ String

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. Corresponds to the JSON property policyScope

Returns:

  • (String) 


4040
4041
4042
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4040

def policy_scope
  @policy_scope
end

#prompt ⇒ String

Required. Policy prompt. Corresponds to the JSON property prompt

Returns:

  • (String) 


4045
4046
4047
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4045

def prompt
  @prompt
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



4052
4053
4054
4055
4056
4057
4058
4059
 
# File 'lib/google/apis/ces_v1/classes.rb', line 4052

def update!(**args)
  @allow_short_utterance = args[:allow_short_utterance] if args.key?(:allow_short_utterance)
  @fail_open = args[:fail_open] if args.key?(:fail_open)
  @max_conversation_messages = args[:max_conversation_messages] if args.key?(:max_conversation_messages)
  @model_settings = args[:model_settings] if args.key?(:model_settings)
  @policy_scope = args[:policy_scope] if args.key?(:policy_scope)
  @prompt = args[:prompt] if args.key?(:prompt)
end