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

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

Overview

See Also:

Instance Attribute Summary collapse

Method Summary

Methods inherited from Internal::Type::BaseModel

#==, ==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, #initialize, 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

This class inherits a constructor from OpenAI::Internal::Type::BaseModel

Instance Attribute Details

#max_completions_tokens ⇒ Integer?

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

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](platform.openai.com/docs/guides/reasoning). 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.

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.

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.

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.

Returns:

  • (Float, nil) 


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

optional :top_p, Float, nil?: true