openai
Version:
The official TypeScript library for the OpenAI API
354 lines • 11.5 kB
TypeScript
import { APIResource } from "../../core/resource.js";
import * as GraderModelsAPI from "./grader-models.js";
import * as Shared from "../shared.js";
import * as ResponsesAPI from "../responses/responses.js";
export declare class GraderModels extends APIResource {
}
/**
* A list of inputs, each of which may be either an input text, output text, input
* image, or input audio object.
*/
export type GraderInputs = Array<string | ResponsesAPI.ResponseInputText | GraderInputs.OutputText | GraderInputs.InputImage | ResponsesAPI.ResponseInputAudio>;
export declare namespace GraderInputs {
/**
* A text output from the model.
*/
interface OutputText {
/**
* The text output from the model.
*/
text: string;
/**
* The type of the output text. Always `output_text`.
*/
type: 'output_text';
}
/**
* An image input block used within EvalItem content arrays.
*/
interface InputImage {
/**
* The URL of the image input.
*/
image_url: string;
/**
* The type of the image input. Always `input_image`.
*/
type: 'input_image';
/**
* The detail level of the image to be sent to the model. One of `high`, `low`, or
* `auto`. Defaults to `auto`.
*/
detail?: string;
}
}
/**
* A LabelModelGrader object which uses a model to assign labels to each item in
* the evaluation.
*/
export interface LabelModelGrader {
input: Array<LabelModelGrader.Input>;
/**
* The labels to assign to each item in the evaluation.
*/
labels: Array<string>;
/**
* The model to use for the evaluation. Must support structured outputs.
*/
model: string;
/**
* The name of the grader.
*/
name: string;
/**
* The labels that indicate a passing result. Must be a subset of labels.
*/
passing_labels: Array<string>;
/**
* The object type, which is always `label_model`.
*/
type: 'label_model';
}
export declare namespace LabelModelGrader {
/**
* A message input to the model with a role indicating instruction following
* hierarchy. Instructions given with the `developer` or `system` role take
* precedence over instructions given with the `user` role. Messages with the
* `assistant` role are presumed to have been generated by the model in previous
* interactions.
*/
interface Input {
/**
* Inputs to the model - can contain template strings. Supports text, output text,
* input images, and input audio, either as a single item or an array of items.
*/
content: string | ResponsesAPI.ResponseInputText | Input.OutputText | Input.InputImage | ResponsesAPI.ResponseInputAudio | GraderModelsAPI.GraderInputs;
/**
* The role of the message input. One of `user`, `assistant`, `system`, or
* `developer`.
*/
role: 'user' | 'assistant' | 'system' | 'developer';
/**
* The type of the message input. Always `message`.
*/
type?: 'message';
}
namespace Input {
/**
* A text output from the model.
*/
interface OutputText {
/**
* The text output from the model.
*/
text: string;
/**
* The type of the output text. Always `output_text`.
*/
type: 'output_text';
}
/**
* An image input block used within EvalItem content arrays.
*/
interface InputImage {
/**
* The URL of the image input.
*/
image_url: string;
/**
* The type of the image input. Always `input_image`.
*/
type: 'input_image';
/**
* The detail level of the image to be sent to the model. One of `high`, `low`, or
* `auto`. Defaults to `auto`.
*/
detail?: string;
}
}
}
/**
* A MultiGrader object combines the output of multiple graders to produce a single
* score.
*/
export interface MultiGrader {
/**
* A formula to calculate the output based on grader results.
*/
calculate_output: string;
/**
* A StringCheckGrader object that performs a string comparison between input and
* reference using a specified operation.
*/
graders: StringCheckGrader | TextSimilarityGrader | PythonGrader | ScoreModelGrader | LabelModelGrader;
/**
* The name of the grader.
*/
name: string;
/**
* The object type, which is always `multi`.
*/
type: 'multi';
}
/**
* A PythonGrader object that runs a python script on the input.
*/
export interface PythonGrader {
/**
* The name of the grader.
*/
name: string;
/**
* The source code of the python script.
*/
source: string;
/**
* The object type, which is always `python`.
*/
type: 'python';
/**
* The image tag to use for the python script.
*/
image_tag?: string;
}
/**
* A ScoreModelGrader object that uses a model to assign a score to the input.
*/
export interface ScoreModelGrader {
/**
* The input messages evaluated by the grader. Supports text, output text, input
* image, and input audio content blocks, and may include template strings.
*/
input: Array<ScoreModelGrader.Input>;
/**
* The model to use for the evaluation.
*/
model: string;
/**
* The name of the grader.
*/
name: string;
/**
* The object type, which is always `score_model`.
*/
type: 'score_model';
/**
* The range of the score. Defaults to `[0, 1]`.
*/
range?: Array<number>;
/**
* The sampling parameters for the model.
*/
sampling_params?: ScoreModelGrader.SamplingParams;
}
export declare namespace ScoreModelGrader {
/**
* A message input to the model with a role indicating instruction following
* hierarchy. Instructions given with the `developer` or `system` role take
* precedence over instructions given with the `user` role. Messages with the
* `assistant` role are presumed to have been generated by the model in previous
* interactions.
*/
interface Input {
/**
* Inputs to the model - can contain template strings. Supports text, output text,
* input images, and input audio, either as a single item or an array of items.
*/
content: string | ResponsesAPI.ResponseInputText | Input.OutputText | Input.InputImage | ResponsesAPI.ResponseInputAudio | GraderModelsAPI.GraderInputs;
/**
* The role of the message input. One of `user`, `assistant`, `system`, or
* `developer`.
*/
role: 'user' | 'assistant' | 'system' | 'developer';
/**
* The type of the message input. Always `message`.
*/
type?: 'message';
}
namespace Input {
/**
* A text output from the model.
*/
interface OutputText {
/**
* The text output from the model.
*/
text: string;
/**
* The type of the output text. Always `output_text`.
*/
type: 'output_text';
}
/**
* An image input block used within EvalItem content arrays.
*/
interface InputImage {
/**
* The URL of the image input.
*/
image_url: string;
/**
* The type of the image input. Always `input_image`.
*/
type: 'input_image';
/**
* The detail level of the image to be sent to the model. One of `high`, `low`, or
* `auto`. Defaults to `auto`.
*/
detail?: string;
}
}
/**
* The sampling parameters for the model.
*/
interface SamplingParams {
/**
* The maximum number of tokens the grader model may generate in its response.
*/
max_completions_tokens?: number | null;
/**
* Constrains effort on reasoning for
* [reasoning models](https://platform.openai.com/docs/guides/reasoning). 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`.
*/
reasoning_effort?: Shared.ReasoningEffort | null;
/**
* A seed value to initialize the randomness, during sampling.
*/
seed?: number | null;
/**
* A higher temperature increases randomness in the outputs.
*/
temperature?: number | null;
/**
* An alternative to temperature for nucleus sampling; 1.0 includes all tokens.
*/
top_p?: number | null;
}
}
/**
* A StringCheckGrader object that performs a string comparison between input and
* reference using a specified operation.
*/
export interface StringCheckGrader {
/**
* The input text. This may include template strings.
*/
input: string;
/**
* The name of the grader.
*/
name: string;
/**
* The string check operation to perform. One of `eq`, `ne`, `like`, or `ilike`.
*/
operation: 'eq' | 'ne' | 'like' | 'ilike';
/**
* The reference text. This may include template strings.
*/
reference: string;
/**
* The object type, which is always `string_check`.
*/
type: 'string_check';
}
/**
* A TextSimilarityGrader object which grades text based on similarity metrics.
*/
export interface TextSimilarityGrader {
/**
* The evaluation metric to use. One of `cosine`, `fuzzy_match`, `bleu`, `gleu`,
* `meteor`, `rouge_1`, `rouge_2`, `rouge_3`, `rouge_4`, `rouge_5`, or `rouge_l`.
*/
evaluation_metric: 'cosine' | 'fuzzy_match' | 'bleu' | 'gleu' | 'meteor' | 'rouge_1' | 'rouge_2' | 'rouge_3' | 'rouge_4' | 'rouge_5' | 'rouge_l';
/**
* The text being graded.
*/
input: string;
/**
* The name of the grader.
*/
name: string;
/**
* The text being graded against.
*/
reference: string;
/**
* The type of grader.
*/
type: 'text_similarity';
}
export declare namespace GraderModels {
export { type GraderInputs as GraderInputs, type LabelModelGrader as LabelModelGrader, type MultiGrader as MultiGrader, type PythonGrader as PythonGrader, type ScoreModelGrader as ScoreModelGrader, type StringCheckGrader as StringCheckGrader, type TextSimilarityGrader as TextSimilarityGrader, };
}
//# sourceMappingURL=grader-models.d.ts.map