@arizeai/phoenix-evals/dist/src/llm/createCorrectnessEvaluator.d.ts

A library for running evaluations for AI use cases

import type { CreateClassificationEvaluatorArgs } from "../types/evals";
import type { ClassificationEvaluator } from "./ClassificationEvaluator";
export interface CorrectnessEvaluatorArgs<RecordType extends Record<string, unknown> = CorrectnessEvaluationRecord> extends Omit<CreateClassificationEvaluatorArgs<RecordType>, "promptTemplate" | "choices" | "optimizationDirection" | "name"> {
    optimizationDirection?: CreateClassificationEvaluatorArgs<RecordType>["optimizationDirection"];
    name?: CreateClassificationEvaluatorArgs<RecordType>["name"];
    choices?: CreateClassificationEvaluatorArgs<RecordType>["choices"];
    promptTemplate?: CreateClassificationEvaluatorArgs<RecordType>["promptTemplate"];
}
/**
 * A record to be evaluated by the correctness evaluator.
 */
export type CorrectnessEvaluationRecord = {
    input: string;
    output: string;
};
/**
 * Creates a correctness evaluator function.
 *
 * This function returns an evaluator that determines whether a given output
 * is factually accurate, complete, logically consistent, and uses precise terminology.
 *
 * @param args - The arguments for creating the correctness evaluator.
 * @param args.model - The model to use for classification.
 * @param args.choices - The possible classification choices (defaults to CORRECTNESS_CHOICES).
 * @param args.promptTemplate - The prompt template to use (defaults to CORRECTNESS_TEMPLATE).
 * @param args.telemetry - The telemetry to use for the evaluator.
 *
 * @returns An evaluator function that takes a {@link CorrectnessEvaluationRecord} and returns a classification result
 * indicating whether the output is correct or incorrect.
 *
 * @example
 * ```ts
 * const evaluator = createCorrectnessEvaluator({ model: openai("gpt-4o-mini") });
 * const result = await evaluator.evaluate({
 *   input: "What is the capital of France?",
 *   output: "Paris is the capital of France.",
 * });
 * console.log(result.label); // "correct" or "incorrect"
 * ```
 */
export declare function createCorrectnessEvaluator<RecordType extends Record<string, unknown> = CorrectnessEvaluationRecord>(args: CorrectnessEvaluatorArgs<RecordType>): ClassificationEvaluator<RecordType>;
//# sourceMappingURL=createCorrectnessEvaluator.d.ts.map