Class: OpenAI::Models::Graders::ScoreModelGrader::SamplingParams

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/graders/score_model_grader.rb,
sig/openai/models/graders/score_model_grader.rbs

Overview

See Also:

  • OpenAI::Models::Graders::ScoreModelGrader#sampling_params

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, 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, #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 ⇒ Object 



178
 
# File 'sig/openai/models/graders/score_model_grader.rbs', line 178

def initialize: (

Instance Attribute Details

#max_completions_tokens ⇒ Integer?

The maximum number of tokens the grader model may generate in its response.

Parameters:

  • value (Integer, nil)

Returns:

  • (Integer, nil) 


223
 
# File 'lib/openai/models/graders/score_model_grader.rb', line 223

optional :max_completions_tokens, Integer, nil?: true

#reasoning_effort ⇒ Symbol, ...

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

  • gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
  • All models before gpt-5.1 default to medium reasoning effort, and do not support none.
  • The gpt-5-pro model defaults to (and only supports) high reasoning effort.
  • xhigh is supported for all models after gpt-5.1-codex-max.

Parameters:

  • value (OpenAI::Models::reasoning_effort, nil)

Returns:



241
 
# File 'lib/openai/models/graders/score_model_grader.rb', line 241

optional :reasoning_effort, enum: -> { OpenAI::ReasoningEffort }, nil?: true

#seed ⇒ Integer?

A seed value to initialize the randomness, during sampling.

Parameters:

  • value (Integer, nil)

Returns:

  • (Integer, nil) 


247
 
# File 'lib/openai/models/graders/score_model_grader.rb', line 247

optional :seed, Integer, nil?: true

#temperature ⇒ Float?

A higher temperature increases randomness in the outputs.

Parameters:

  • value (Float, nil)

Returns:

  • (Float, nil) 


253
 
# File 'lib/openai/models/graders/score_model_grader.rb', line 253

optional :temperature, Float, nil?: true

#top_p ⇒ Float?

An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

Parameters:

  • value (Float, nil)

Returns:

  • (Float, nil) 


259
 
# File 'lib/openai/models/graders/score_model_grader.rb', line 259

optional :top_p, Float, nil?: true

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


186
 
# File 'sig/openai/models/graders/score_model_grader.rbs', line 186

def to_hash: -> {