Class: OpenAI::Models::Evals::RunCreateParams::DataSource::CreateEvalResponsesRunDataSource::SamplingParams

Inherits:
Internal::Type::BaseModel
  • Object
show all
Defined in:
lib/openai/models/evals/run_create_params.rb,
sig/openai/models/evals/run_create_params.rbs

Overview

See Also:

  • OpenAI::Models::Evals::RunCreateParams::DataSource::CreateEvalResponsesRunDataSource#sampling_params

Defined Under Namespace

Classes: Text

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(max_completion_tokens: nil, reasoning_effort: nil, seed: nil, temperature: nil, text: nil, tools: nil, top_p: nil) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Evals::RunCreateParams::DataSource::CreateEvalResponsesRunDataSource::SamplingParams for more details.

Parameters:




# File 'lib/openai/models/evals/run_create_params.rb', line 665

Instance Attribute Details

#max_completion_tokens ⇒ Integer?

The maximum number of tokens in the generated output.

Parameters:

  • (Integer)

Returns:

  • (Integer, nil) 


597
 
# File 'lib/openai/models/evals/run_create_params.rb', line 597

optional :max_completion_tokens, Integer

#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:



615
 
# File 'lib/openai/models/evals/run_create_params.rb', line 615

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

#seed ⇒ Integer?

A seed value to initialize the randomness, during sampling.

Parameters:

  • (Integer)

Returns:

  • (Integer, nil) 


621
 
# File 'lib/openai/models/evals/run_create_params.rb', line 621

optional :seed, Integer

#temperature ⇒ Float?

A higher temperature increases randomness in the outputs.

Parameters:

  • (Float)

Returns:

  • (Float, nil) 


627
 
# File 'lib/openai/models/evals/run_create_params.rb', line 627

optional :temperature, Float

#text ⇒ OpenAI::Models::Evals::RunCreateParams::DataSource::CreateEvalResponsesRunDataSource::SamplingParams::Text?

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

Returns:



637
638
 
# File 'lib/openai/models/evals/run_create_params.rb', line 637

optional :text,
-> { OpenAI::Evals::RunCreateParams::DataSource::CreateEvalResponsesRunDataSource::SamplingParams::Text }

#tools ⇒ Array<OpenAI::Models::Responses::FunctionTool, OpenAI::Models::Responses::FileSearchTool, OpenAI::Models::Responses::ComputerTool, OpenAI::Models::Responses::ComputerUsePreviewTool, OpenAI::Models::Responses::Tool::Mcp, OpenAI::Models::Responses::Tool::CodeInterpreter, OpenAI::Models::Responses::Tool::ImageGeneration, OpenAI::Models::Responses::Tool::LocalShell, OpenAI::Models::Responses::FunctionShellTool, OpenAI::Models::Responses::CustomTool, OpenAI::Models::Responses::NamespaceTool, OpenAI::Models::Responses::ToolSearchTool, OpenAI::Models::Responses::ApplyPatchTool, OpenAI::Models::Responses::WebSearchTool, OpenAI::Models::Responses::WebSearchPreviewTool>?

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

The two categories of tools you can provide the model are:

  • Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  • Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code. Learn more about function calling.

Returns:



657
 
# File 'lib/openai/models/evals/run_create_params.rb', line 657

optional :tools, -> { OpenAI::Internal::Type::ArrayOf[union: OpenAI::Responses::Tool] }

#top_p ⇒ Float?

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

Parameters:

  • (Float)

Returns:

  • (Float, nil) 


663
 
# File 'lib/openai/models/evals/run_create_params.rb', line 663

optional :top_p, Float

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


477
 
# File 'sig/openai/models/evals/run_create_params.rbs', line 477

def to_hash: -> {