class

OpenAI::CreateEvalResponsesRunDataSource

Inherits JSON::Serializable < Reference < Object

A ResponsesRunDataSource object describing a model sampling configuration.

Constructors

new(pull : JSON::PullParser)
Source
new(type_value : CreateEvalResponsesRunDataSourceType = CreateEvalResponsesRunDataSourceType::Responses, input_messages : CreateEvalResponsesRunDataSourceInputMessages | Nil = nil, sampling_params : CreateEvalResponsesRunDataSourceSamplingParams | Nil = nil, model : String | Nil = nil, source : CreateEvalResponsesRunDataSourceSource = EvalJsonlFileContentSource.new)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

input_messages

Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, item.input_trajectory), or a template with variable references to the item namespace.

Source
input_messages=(input_messages : CreateEvalResponsesRunDataSourceInputMessages | Nil)

Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, item.input_trajectory), or a template with variable references to the item namespace.

Source
model

The name of the model to use for generating completions (e.g. "o3-mini").

Source
model=(model : String | Nil)

The name of the model to use for generating completions (e.g. "o3-mini").

Source
sampling_params
Source
sampling_params=(sampling_params : CreateEvalResponsesRunDataSourceSamplingParams | Nil)
Source
source

Determines what populates the item namespace in this run's data source.

Source
source=(source : CreateEvalResponsesRunDataSourceSource)

Determines what populates the item namespace in this run's data source.

Source
type_value

The type of run data source. Always responses.

Source
type_value=(type_value : CreateEvalResponsesRunDataSourceType)

The type of run data source. Always responses.

Source