Class: Google::Cloud::Ces::V1beta::Guardrail::LlmPromptSecurity

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/ces/v1beta/guardrail.rb

Overview

Guardrail that blocks the conversation if the input is considered unsafe based on the LLM classification.

Defined Under Namespace

Classes: DefaultSecuritySettings

Instance Attribute Summary collapse

Instance Attribute Details

#custom_policy ⇒ ::Google::Cloud::Ces::V1beta::Guardrail::LlmPolicy

Returns Optional. Use a user-defined LlmPolicy to configure the security guardrail.

Note: The following fields are mutually exclusive: custom_policy, default_settings. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:

  • (::Google::Cloud::Ces::V1beta::Guardrail::LlmPolicy) —

    Optional. Use a user-defined LlmPolicy to configure the security guardrail.

    Note: The following fields are mutually exclusive: custom_policy, default_settings. If a field in that set is populated, all other fields in the set will automatically be cleared.



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'proto_docs/google/cloud/ces/v1beta/guardrail.rb', line 152

class LlmPromptSecurity
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration for default system security settings.
  # @!attribute [r] default_prompt_template
  #   @return [::String]
  #     Output only. The default prompt template used by the system.
  #     This field is for display purposes to show the user what prompt
  #     the system uses by default. It is OUTPUT_ONLY.
  class DefaultSecuritySettings
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#default_settings ⇒ ::Google::Cloud::Ces::V1beta::Guardrail::LlmPromptSecurity::DefaultSecuritySettings

Returns Optional. Use the system's predefined default security settings. To select this mode, include an empty 'default_settings' message in the request. The 'default_prompt_template' field within will be populated by the server in the response.

Note: The following fields are mutually exclusive: default_settings, custom_policy. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:

  • (::Google::Cloud::Ces::V1beta::Guardrail::LlmPromptSecurity::DefaultSecuritySettings) —

    Optional. Use the system's predefined default security settings. To select this mode, include an empty 'default_settings' message in the request. The 'default_prompt_template' field within will be populated by the server in the response.

    Note: The following fields are mutually exclusive: default_settings, custom_policy. If a field in that set is populated, all other fields in the set will automatically be cleared.



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'proto_docs/google/cloud/ces/v1beta/guardrail.rb', line 152

class LlmPromptSecurity
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration for default system security settings.
  # @!attribute [r] default_prompt_template
  #   @return [::String]
  #     Output only. The default prompt template used by the system.
  #     This field is for display purposes to show the user what prompt
  #     the system uses by default. It is OUTPUT_ONLY.
  class DefaultSecuritySettings
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#fail_open ⇒ ::Boolean

Returns Optional. Determines the behavior when the guardrail encounters an LLM error.

  • If true: the guardrail is bypassed.
  • If false (default): the guardrail triggers/blocks.

Note: If a custom policy is provided, this field is ignored in favor of the policy's 'fail_open' configuration.

Returns:

  • (::Boolean) —

    Optional. Determines the behavior when the guardrail encounters an LLM error.

    • If true: the guardrail is bypassed.
    • If false (default): the guardrail triggers/blocks.

    Note: If a custom policy is provided, this field is ignored in favor of the policy's 'fail_open' configuration.



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'proto_docs/google/cloud/ces/v1beta/guardrail.rb', line 152

class LlmPromptSecurity
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration for default system security settings.
  # @!attribute [r] default_prompt_template
  #   @return [::String]
  #     Output only. The default prompt template used by the system.
  #     This field is for display purposes to show the user what prompt
  #     the system uses by default. It is OUTPUT_ONLY.
  class DefaultSecuritySettings
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end