Accuracy Evaluation

import { AccuracyEval } from "@agentium/eval";
import { Agent, openai } from "@agentium/core";

const agent = new Agent({ name: "qa-bot", model: openai("gpt-4o") });

const eval = new AccuracyEval({
  name: "qa-accuracy",
  agent,
  judge: openai("gpt-4o-mini"),
  cases: [
    { name: "capital", input: "What is the capital of France?", expected: "Paris" },
    { name: "math", input: "What is 2+2?", expected: "4" },
  ],
  threshold: 0.8,
});

const result = await eval.run();
console.log(`Passed: ${result.passed}/${result.total}, Avg: ${result.averageScore}`);