Class: Google::Apis::FirebasemlV2beta::GoogleCloudAiplatformV1beta1ModelArmorConfig

Inherits:

Object

• Object
• Google::Apis::FirebasemlV2beta::GoogleCloudAiplatformV1beta1ModelArmorConfig

Includes:

Core::Hashable, Core::JsonObjectSupport

Defined in:

lib/google/apis/firebaseml_v2beta/classes.rb,
lib/google/apis/firebaseml_v2beta/representations.rb,
lib/google/apis/firebaseml_v2beta/representations.rb

Overview

Configuration for Model Armor. Model Armor is a Google Cloud service that provides safety and security filtering for prompts and responses. It helps protect your AI applications from risks such as harmful content, sensitive data leakage, and prompt injection attacks.

Instance Attribute Summary

• #prompt_template_name ⇒ String

  Optional.

• #response_template_name ⇒ String

  Optional.

Instance Method Summary

• #initialize(**args) ⇒ GoogleCloudAiplatformV1beta1ModelArmorConfig constructor

  A new instance of GoogleCloudAiplatformV1beta1ModelArmorConfig.

• #update!(**args) ⇒ Object

  Update properties of this object.

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1ModelArmorConfig

Returns a new instance of GoogleCloudAiplatformV1beta1ModelArmorConfig.

# File 'lib/google/apis/firebaseml_v2beta/classes.rb', line 2418

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

Instance Attribute Details

#prompt_template_name ⇒ String

Optional. The resource name of the Model Armor template to use for prompt screening. A Model Armor template is a set of customized filters and thresholds that define how Model Armor screens content. If specified, Model Armor will use this template to check the user's prompt for safety and security risks before it is sent to the model. The name must be in the format projects/project/locations/location/templates/template`. Corresponds to the JSON propertypromptTemplateName`

Returns:

• (String)

# File 'lib/google/apis/firebaseml_v2beta/classes.rb', line 2406

def prompt_template_name
  @prompt_template_name
end

#response_template_name ⇒ String

Optional. The resource name of the Model Armor template to use for response screening. A Model Armor template is a set of customized filters and thresholds that define how Model Armor screens content. If specified, Model Armor will use this template to check the model's response for safety and security risks before it is returned to the user. The name must be in the format projects/project/locations/location/templates/template`. Corresponds to the JSON propertyresponseTemplateName`

Returns:

• (String)

# File 'lib/google/apis/firebaseml_v2beta/classes.rb', line 2416

def response_template_name
  @response_template_name
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object

# File 'lib/google/apis/firebaseml_v2beta/classes.rb', line 2423

def update!(**args)
  @prompt_template_name = args[:prompt_template_name] if args.key?(:prompt_template_name)
  @response_template_name = args[:response_template_name] if args.key?(:response_template_name)
end