Class: OpenAI::Resources::FineTuning::Alpha::Graders

Inherits:

Object

• Object
• OpenAI::Resources::FineTuning::Alpha::Graders

Defined in:

lib/openai/resources/fine_tuning/alpha/graders.rb,
sig/openai/resources/fine_tuning/alpha/graders.rbs

Overview

Manage fine-tuning jobs to tailor a model to your specific training data.

Instance Method Summary

• #initialize(client:) ⇒ Graders constructor private

  A new instance of Graders.

• #run(grader:, model_sample:, item: nil, request_options: {}) ⇒ OpenAI::Models::FineTuning::Alpha::GraderRunResponse

  Run a grader.

• #validate(grader:, request_options: {}) ⇒ OpenAI::Models::FineTuning::Alpha::GraderValidateResponse

  Validate a grader.

Constructor Details

#initialize(client:) ⇒ Graders

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of Graders.

Parameters:

• client (OpenAI::Client)
• client: (OpenAI::Client)

# File 'lib/openai/resources/fine_tuning/alpha/graders.rb', line 73

def initialize(client:)
  @client = client
end

Instance Method Details

#run(grader:, model_sample:, item: nil, request_options: {}) ⇒ OpenAI::Models::FineTuning::Alpha::GraderRunResponse

Run a grader.

Parameters:

• grader (OpenAI::Models::Graders::StringCheckGrader, OpenAI::Models::Graders::TextSimilarityGrader, OpenAI::Models::Graders::PythonGrader, OpenAI::Models::Graders::ScoreModelGrader, OpenAI::Models::Graders::MultiGrader) —

  The grader used for the fine-tuning job.

• model_sample (String) —

  The model sample to be evaluated. This value will be used to populate the sample namespace. See the guide for more details. The output_json variable will be populated if the model sample is a valid JSON string.

• item (Object) —

  The dataset item provided to the grader. This will be used to populate the item namespace. See the guide for more details.

• request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

• (OpenAI::Models::FineTuning::Alpha::GraderRunResponse)

See Also:

• Models::FineTuning::Alpha::GraderRunParams

# File 'lib/openai/resources/fine_tuning/alpha/graders.rb', line 34

def run(params)
  parsed, options = OpenAI::FineTuning::Alpha::GraderRunParams.dump_request(params)
  @client.request(
    method: :post,
    path: "fine_tuning/alpha/graders/run",
    body: parsed,
    model: OpenAI::Models::FineTuning::Alpha::GraderRunResponse,
    security: {bearer_auth: true},
    options: options
  )
end

#validate(grader:, request_options: {}) ⇒ OpenAI::Models::FineTuning::Alpha::GraderValidateResponse

Validate a grader.

Parameters:

• grader (OpenAI::Models::Graders::StringCheckGrader, OpenAI::Models::Graders::TextSimilarityGrader, OpenAI::Models::Graders::PythonGrader, OpenAI::Models::Graders::ScoreModelGrader, OpenAI::Models::Graders::MultiGrader) —

  The grader used for the fine-tuning job.

• request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

• (OpenAI::Models::FineTuning::Alpha::GraderValidateResponse)

See Also:

• Models::FineTuning::Alpha::GraderValidateParams

# File 'lib/openai/resources/fine_tuning/alpha/graders.rb', line 58

def validate(params)
  parsed, options = OpenAI::FineTuning::Alpha::GraderValidateParams.dump_request(params)
  @client.request(
    method: :post,
    path: "fine_tuning/alpha/graders/validate",
    body: parsed,
    model: OpenAI::Models::FineTuning::Alpha::GraderValidateResponse,
    security: {bearer_auth: true},
    options: options
  )
end