@arizeai/phoenix-evals/dist/src/llm/createToolInvocationEvaluator.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.createToolInvocationEvaluator = createToolInvocationEvaluator;
const default_templates_1 = require("../__generated__/default_templates");
const createClassificationEvaluator_1 = require("./createClassificationEvaluator");
/**
 * Creates a tool invocation evaluator function.
 *
 * This function returns an evaluator that determines whether a tool was invoked
 * correctly with proper arguments, formatting, and safe content.
 *
 * The evaluator checks for:
 * - Properly structured JSON (if applicable)
 * - All required fields/parameters present
 * - No hallucinated or nonexistent fields
 * - Argument values matching user query and schema expectations
 * - No unsafe content (e.g., PII) in arguments
 *
 * @param args - The arguments for creating the tool invocation evaluator.
 * @param args.model - The model to use for classification.
 * @param args.choices - The possible classification choices (defaults to correct/incorrect).
 * @param args.promptTemplate - The prompt template to use (defaults to TOOL_INVOCATION_TEMPLATE).
 * @param args.telemetry - The telemetry to use for the evaluator.
 *
 * @returns An evaluator function that takes a {@link ToolInvocationEvaluationRecord} and returns
 * a classification result indicating whether the tool invocation is correct or incorrect.
 *
 * @example
 * ```ts
 * const evaluator = createToolInvocationEvaluator({ model: openai("gpt-4o-mini") });
 *
 * // Example with JSON schema format for available tools
 * const result = await evaluator.evaluate({
 *   input: "User: Book a flight from NYC to LA for tomorrow",
 *   availableTools: JSON.stringify({
 *     name: "book_flight",
 *     description: "Book a flight between two cities",
 *     parameters: {
 *       type: "object",
 *       properties: {
 *         origin: { type: "string", description: "Departure city code" },
 *         destination: { type: "string", description: "Arrival city code" },
 *         date: { type: "string", description: "Flight date in YYYY-MM-DD" }
 *       },
 *       required: ["origin", "destination", "date"]
 *     }
 *   }),
 *   toolSelection: 'book_flight(origin="NYC", destination="LA", date="2024-01-15")'
 * });
 * console.log(result.label); // "correct" or "incorrect"
 * ```
 */
function createToolInvocationEvaluator(args) {
    const { choices = default_templates_1.TOOL_INVOCATION_CLASSIFICATION_EVALUATOR_CONFIG.choices, promptTemplate = default_templates_1.TOOL_INVOCATION_CLASSIFICATION_EVALUATOR_CONFIG.template, optimizationDirection = default_templates_1.TOOL_INVOCATION_CLASSIFICATION_EVALUATOR_CONFIG.optimizationDirection, name = default_templates_1.TOOL_INVOCATION_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=createToolInvocationEvaluator.js.map