如何在单个评估器中返回多个分数

def multiple_scores(outputs: dict, reference_outputs: dict) -> list[dict]:
    # 替换为真实的评估逻辑。
    precision = 0.8
    recall = 0.9
    f1 = 0.85
    return [
        {"key": "precision", "score": precision},
        {"key": "recall", "score": recall},
        {"key": "f1", "score": f1},
    ]

import type { Run, Example } from "langsmith/schemas";

function multipleScores(rootRun: Run, example: Example) {
  // 你的评估逻辑在这里
  return {
      results: [
          { key: "precision", score: 0.8 },
          { key: "recall", score: 0.9 },
          { key: "f1", score: 0.85 },
      ],
  };
}