class

OpenAI::CreateEvalResponsesRunDataSourceSamplingParams

Inherits JSON::Serializable < Reference < Object

Constructors

new(pull : JSON::PullParser)
Source
new(reasoning_effort : ReasoningEffort | Nil = nil, temperature : Float64 | Nil = nil, max_completion_tokens : Int64 | Nil = nil, top_p : Float64 | Nil = nil, seed : Int64 | Nil = nil, tools : Array(Tool) | Nil = nil, text : CreateEvalResponsesRunDataSourceSamplingParamsText | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

max_completion_tokens

The maximum number of tokens in the generated output.

Source
max_completion_tokens=(max_completion_tokens : Int64 | Nil)

The maximum number of tokens in the generated output.

Source
reasoning_effort
Source
reasoning_effort=(reasoning_effort : ReasoningEffort | Nil)
Source
seed

A seed value to initialize the randomness, during sampling.

Source
seed=(seed : Int64 | Nil)

A seed value to initialize the randomness, during sampling.

Source
temperature

A higher temperature increases randomness in the outputs.

Source
temperature=(temperature : Float64 | Nil)

A higher temperature increases randomness in the outputs.

Source
text

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

Source
text=(text : CreateEvalResponsesRunDataSourceSamplingParamsText | Nil)

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

Source
tools

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.
Source
tools=(tools : Array(Tool) | Nil)

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.
Source
top_p

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

Source
top_p=(top_p : Float64 | Nil)

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

Source