@arizeai/phoenix-evals/dist/src/llm/createToolSelectionEvaluator.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.createToolSelectionEvaluator = createToolSelectionEvaluator;
const default_templates_1 = require("../__generated__/default_templates");
const createClassificationEvaluator_1 = require("./createClassificationEvaluator");
/**
 * Creates a tool selection evaluator function.
 *
 * This function returns an evaluator that determines whether the correct tool
 * was selected for a given context. Unlike the tool invocation evaluator which
 * checks if the tool was called correctly with proper arguments, this evaluator
 * focuses on whether the right tool was chosen in the first place.
 *
 * The evaluator checks for:
 * - Whether the LLM chose the best available tool for the user query
 * - Whether the tool name exists in the available tools list
 * - Whether the correct number of tools were selected for the task
 * - Whether the tool selection is safe and appropriate
 *
 * @param args - The arguments for creating the tool selection 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_SELECTION_TEMPLATE).
 * @param args.telemetry - The telemetry to use for the evaluator.
 *
 * @returns An evaluator function that takes a {@link ToolSelectionEvaluationRecord} and returns
 * a classification result indicating whether the tool selection is correct or incorrect.
 *
 * @example
 * ```ts
 * const evaluator = createToolSelectionEvaluator({ model: openai("gpt-4o-mini") });
 *
 * const result = await evaluator.evaluate({
 *   input: "User: What is the weather in San Francisco?",
 *   availableTools: `WeatherTool: Get the current weather for a location.
 * NewsTool: Stay connected to global events with our up-to-date news around the world.
 * MusicTool: Create playlists, search for music, and check the latest music trends.`,
 *   toolSelection: "WeatherTool"
 * });
 * console.log(result.label); // "correct" or "incorrect"
 * ```
 */
function createToolSelectionEvaluator(args) {
    const { choices = default_templates_1.TOOL_SELECTION_CLASSIFICATION_EVALUATOR_CONFIG.choices, promptTemplate = default_templates_1.TOOL_SELECTION_CLASSIFICATION_EVALUATOR_CONFIG.template, optimizationDirection = default_templates_1.TOOL_SELECTION_CLASSIFICATION_EVALUATOR_CONFIG.optimizationDirection, name = default_templates_1.TOOL_SELECTION_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=createToolSelectionEvaluator.js.map