Module: Deeprails::Models::DefendResponse::AutomaticHallucinationToleranceLevel

Extended by:

Internal::Type::Enum

Defined in:

lib/deeprails/models/defend_response.rb

Constant Summary

LOW =

:low

MEDIUM =

:medium

HIGH =

:high

Instance Method Summary

• #initialize(automatic_hallucination_tolerance_levels:, capabilities:, created_at:, custom_hallucination_threshold_values:, description:, events:, files:, name:, status:, threshold_type:, updated_at:, workflow_id:, improvement_action: nil, stats: nil) ⇒ Object

  Some parameter documentations has been truncated, see Deeprails::Models::DefendResponse for more details.

Methods included from Internal::Type::Enum

==, ===, coerce, dump, hash, inspect, to_sorbet_type, values

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, inspect, #inspect, meta_info, new_coerce_state, type_info

Instance Method Details

#initialize(automatic_hallucination_tolerance_levels:, capabilities:, created_at:, custom_hallucination_threshold_values:, description:, events:, files:, name:, status:, threshold_type:, updated_at:, workflow_id:, improvement_action: nil, stats: nil) ⇒ Object

Some parameter documentations has been truncated, see Deeprails::Models::DefendResponse for more details.

Parameters:

• automatic_hallucination_tolerance_levels (Hash{Symbol=>Symbol, Deeprails::Models::DefendResponse::AutomaticHallucinationToleranceLevel}) —

  Mapping of guardrail metric names to tolerance values. Values can be strings (‘l

• capabilities (Array<Deeprails::Models::DefendResponse::Capability>) —

  Extended AI capabilities available to the event, if any. Can be ‘web_search` and

• created_at (Time) —

  The time the workflow was created in UTC.

• custom_hallucination_threshold_values (Hash{Symbol=>Float}) —

  Mapping of guardrail metric names to threshold values. Values can be floating po

• description (String) —

  A description for the workflow, to help you remember what that workflow means to

• events (Array<Deeprails::Models::DefendResponse::Event>) —

  An array of events associated with this workflow.

• files (Array<Deeprails::Models::DefendResponse::File>) —

  List of files associated with the workflow. If this is not empty, models can sea

• name (String) —

  A human-readable name for the workflow that will correspond to it’s workflow ID.

• status (Symbol, Deeprails::Models::DefendResponse::Status) —

  Status of the selected workflow. May be ‘inactive` or `active`. Inactive workf

• threshold_type (Symbol, Deeprails::Models::DefendResponse::ThresholdType) —

  Type of thresholds used to evaluate the event.

• updated_at (Time) —

  The most recent time the workflow was updated in UTC.

• workflow_id (String) —

  A unique workflow ID used to identify the workflow in other endpoints.

• improvement_action (Symbol, Deeprails::Models::DefendResponse::ImprovementAction) (defaults to: nil) —

  The action used to improve outputs that fail one or more guardrail metrics for t

• stats (Deeprails::Models::DefendResponse::Stats) (defaults to: nil)

# File 'lib/deeprails/models/defend_response.rb', line 130

module AutomaticHallucinationToleranceLevel
  extend Deeprails::Internal::Type::Enum

  LOW = :low
  MEDIUM = :medium
  HIGH = :high

  # @!method self.values
  #   @return [Array<Symbol>]
end