@arizeai/phoenix-evals/dist/src/llm/createHallucinationEvaluator.js

A library for running evaluations for AI use cases

"use strict";
var __rest = (this && this.__rest) || function (s, e) {
    var t = {};
    for (var p in s) if (Object.prototype.hasOwnProperty.call(s, p) && e.indexOf(p) < 0)
        t[p] = s[p];
    if (s != null && typeof Object.getOwnPropertySymbols === "function")
        for (var i = 0, p = Object.getOwnPropertySymbols(s); i < p.length; i++) {
            if (e.indexOf(p[i]) < 0 && Object.prototype.propertyIsEnumerable.call(s, p[i]))
                t[p[i]] = s[p[i]];
        }
    return t;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.createHallucinationEvaluator = createHallucinationEvaluator;
const default_templates_1 = require("../__generated__/default_templates");
const createClassificationEvaluator_1 = require("./createClassificationEvaluator");
/**
 * Creates a hallucination evaluator function.
 *
 * This function returns an evaluator that detects whether an assistant's latest
 * response contains claims that are not grounded in — unsupported by, or
 * contradicting — the conversation. Unlike the faithfulness evaluator, which
 * grounds a response against a specific provided context (e.g. retrieved
 * documents), this grounds it against the conversation itself.
 *
 * @param args - The arguments for creating the hallucination evaluator.
 * @param args.model - The model to use for classification.
 * @param args.choices - The possible classification choices (defaults to hallucinated/grounded).
 * @param args.promptTemplate - The prompt template to use (defaults to HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.template).
 * @param args.telemetry - The telemetry to use for the evaluator.
 *
 * @returns An evaluator function that takes a {@link HallucinationEvaluationRecord} and returns a classification result
 * indicating whether the response is grounded or hallucinated relative to the conversation.
 *
 * @example
 * ```ts
 * const evaluator = createHallucinationEvaluator({ model: openai("gpt-4o-mini") });
 * const result = await evaluator.evaluate({
 *   input:
 *     "User: What's our refund window?\nTool (lookup_policy): Refunds: 30 days from delivery.\nAssistant: 30 days from delivery.\nUser: And for electronics?",
 *   output: "Electronics can be returned within 90 days.",
 * });
 * console.log(result.label); // "hallucinated"
 * ```
 */
function createHallucinationEvaluator(args) {
    const { choices = default_templates_1.HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.choices, promptTemplate = default_templates_1.HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.template, optimizationDirection = default_templates_1.HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.optimizationDirection, name = default_templates_1.HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.name } = args, rest = __rest(args, ["choices", "promptTemplate", "optimizationDirection", "name"]);
    return (0, createClassificationEvaluator_1.createClassificationEvaluator)(Object.assign(Object.assign({}, rest), { promptTemplate,
        choices,
        optimizationDirection,
        name }));
}
//# sourceMappingURL=createHallucinationEvaluator.js.map