Class Evals

constructor

• new Evals(client): Evals

• Parameters

  • client: OpenAI

  Returns Evals

runs

create

• create(body, options?): APIPromise<EvalCreateResponse>

• Create the structure of an evaluation that can be used to test a model's performance. An evaluation is a set of testing criteria and a datasource. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources. For more information, see the Evals guide.

  Parameters

  • body: EvalCreateParams
  • Optionaloptions: RequestOptions<unknown>

  Returns APIPromise<EvalCreateResponse>

del

• del(evalId, options?): APIPromise<EvalDeleteResponse>

• Delete an evaluation.

  Parameters

  • evalId: string
  • Optionaloptions: RequestOptions<unknown>

  Returns APIPromise<EvalDeleteResponse>

list

• list(query?, options?): PagePromise<EvalListResponsesPage, EvalListResponse>

• List evaluations for a project.

  Parameters

  • Optionalquery: EvalListParams
  • Optionaloptions: RequestOptions<unknown>

  Returns PagePromise<EvalListResponsesPage, EvalListResponse>
• list(options?): PagePromise<EvalListResponsesPage, EvalListResponse>

• Parameters

  • Optionaloptions: RequestOptions<unknown>

  Returns PagePromise<EvalListResponsesPage, EvalListResponse>

retrieve

• retrieve(evalId, options?): APIPromise<EvalRetrieveResponse>

• Get an evaluation by ID.

  Parameters

  • evalId: string
  • Optionaloptions: RequestOptions<unknown>

  Returns APIPromise<EvalRetrieveResponse>

update

• update(evalId, body, options?): APIPromise<EvalUpdateResponse>

• Update certain properties of an evaluation.

  Parameters

  • evalId: string
  • body: EvalUpdateParams
  • Optionaloptions: RequestOptions<unknown>

  Returns APIPromise<EvalUpdateResponse>