UNPKG

@arizeai/phoenix-evals

Version:
42 lines 2.31 kB
import { HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG } from "../__generated__/default_templates/index.js"; import { createClassificationEvaluator } from "./createClassificationEvaluator.js"; /** * 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" * ``` */ export function createHallucinationEvaluator(args) { const { choices = HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.choices, promptTemplate = HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.template, optimizationDirection = HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.optimizationDirection, name = HALLUCINATION_CLASSIFICATION_EVALUATOR_CONFIG.name, ...rest } = args; return createClassificationEvaluator({ ...rest, promptTemplate, choices, optimizationDirection, name, }); } //# sourceMappingURL=createHallucinationEvaluator.js.map