Class: Aws::QConnect::Types::GuardrailContentFilterConfig

Inherits:
Struct
  • Object
show all
Defined in:
gems/aws-sdk-qconnect/lib/aws-sdk-qconnect/types.rb

Overview

Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.

  • Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).

  • Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.

  • Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.

  • Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.

Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.

See Also:

Constant Summary collapse

SENSITIVE = 
[:type, :input_strength, :output_strength]

Instance Attribute Summary collapse

Instance Attribute Details

#input_strength ⇒ String

The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

Returns:

  • (String) 


5519
5520
5521
5522
5523
5524
5525
 
# File 'gems/aws-sdk-qconnect/lib/aws-sdk-qconnect/types.rb', line 5519

class GuardrailContentFilterConfig < Struct.new(
  :type,
  :input_strength,
  :output_strength)
  SENSITIVE = [:type, :input_strength, :output_strength]
  include Aws::Structure
end

#output_strength ⇒ String

The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

Returns:

  • (String) 


5519
5520
5521
5522
5523
5524
5525
 
# File 'gems/aws-sdk-qconnect/lib/aws-sdk-qconnect/types.rb', line 5519

class GuardrailContentFilterConfig < Struct.new(
  :type,
  :input_strength,
  :output_strength)
  SENSITIVE = [:type, :input_strength, :output_strength]
  include Aws::Structure
end

#type ⇒ String

The harmful category that the content filter is applied to.

Returns:

  • (String) 


5519
5520
5521
5522
5523
5524
5525
 
# File 'gems/aws-sdk-qconnect/lib/aws-sdk-qconnect/types.rb', line 5519

class GuardrailContentFilterConfig < Struct.new(
  :type,
  :input_strength,
  :output_strength)
  SENSITIVE = [:type, :input_strength, :output_strength]
  include Aws::Structure
end