Class: OpenAI::Models::EvalListResponse::TestingCriterion::EvalGraderScoreModel

Inherits:
Graders::ScoreModelGrader show all
Defined in:
lib/openai/models/eval_list_response.rb,
sig/openai/models/eval_list_response.rbs

Instance Attribute Summary collapse

Attributes inherited from Graders::ScoreModelGrader

#input, #model, #name, #range, #sampling_params, #type

Attributes inherited from Internal::Type::BaseModel

#last_response

Instance Method Summary collapse

Methods inherited from Graders::ScoreModelGrader

values

Methods inherited from Internal::Type::BaseModel

==, #==, #[], #_request_id, #_set_last_response, coerce, #deconstruct_keys, #deep_to_h, dump, #encode_with, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

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

Methods included from Internal::Util::SorbetRuntimeSupport

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

Constructor Details

#initialize(input:, model:, name:, range: nil, sampling_params: nil, pass_threshold: nil, type: :score_model) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::EvalListResponse::TestingCriterion::EvalGraderScoreModel for more details.

A ScoreModelGrader object that uses a model to assign a score to the input.

Parameters:

  • input (Array<OpenAI::Models::Graders::ScoreModelGrader::Input>) —

    The input messages evaluated by the grader. Supports text, output text, input im

  • model (String) —

    The model to use for the evaluation.

  • name (String) —

    The name of the grader.

  • range (Array<Float>) (defaults to: nil) —

    The range of the score. Defaults to [0, 1].

  • sampling_params (OpenAI::Models::Graders::ScoreModelGrader::SamplingParams) (defaults to: nil) —

    The sampling parameters for the model.

  • pass_threshold (Float) (defaults to: nil) —

    The threshold for the score.

  • type (Symbol, :score_model) (defaults to: :score_model) —

    The object type, which is always score_model.




# File 'lib/openai/models/eval_list_response.rb', line 227

Instance Attribute Details

#pass_threshold ⇒ Float?

The threshold for the score.

Parameters:

  • _ (Float)

Returns:

  • (Float, nil) 


225
 
# File 'lib/openai/models/eval_list_response.rb', line 225

optional :pass_threshold, Float

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


188
 
# File 'sig/openai/models/eval_list_response.rbs', line 188

def to_hash: -> {