如何在本地读取实验结果

from langsmith import Client
import random

client = Client()

def target(inputs):
    """您的应用程序或 LLM 链"""
    return {"output": "MY OUTPUT"}

def evaluator(run, example):
    """您的评估器函数"""
    return {"key": "randomness", "score": random.randint(0, 1)}

# 使用 blocking=False 运行评估以获取迭代器
streamed_results = client.evaluate(
    target,
    data="MY_DATASET_NAME",
    evaluators=[evaluator],
    blocking=False
)

# 在结果流式传入时收集它们
aggregated_results = []
for result in streamed_results:
    aggregated_results.append(result)

# 单独的循环以避免与 evaluate() 的日志同时记录
for result in aggregated_results:
    print("Input:", result["run"].inputs)
    print("Output:", result["run"].outputs)
    print("Evaluation Results:", result["evaluation_results"]["results"])
    print("--------------------------------")

Input: {'input': 'MY INPUT'}
Output: {'output': 'MY OUTPUT'}
Evaluation Results: [EvaluationResult(key='randomness', score=1, value=None, comment=None, correction=None, evaluator_info={}, feedback_config=None, source_run_id=UUID('7ebb4900-91c0-40b0-bb10-f2f6a451fd3c'), target_run_id=None, extra=None)]
--------------------------------

from langsmith import Client
import sys

client = Client()

def my_application(inputs):
    # 您的应用程序逻辑
    return {"response": "..."}

def accuracy_evaluator(run, example):
    # 您的评估逻辑
    is_correct = run.outputs["response"] == example.outputs["expected"]
    return {"key": "accuracy", "score": 1 if is_correct else 0}

# 运行评估
results = client.evaluate(
    my_application,
    data="my_test_dataset",
    evaluators=[accuracy_evaluator],
    blocking=False
)

# 计算聚合指标
total_score = 0
count = 0

for result in results:
    eval_result = result["evaluation_results"]["results"][0]
    total_score += eval_result.score
    count += 1

average_accuracy = total_score / count

print(f"Average accuracy: {average_accuracy:.2%}")

# 如果准确率太低则构建失败
if average_accuracy < 0.85:
    print("❌ Evaluation failed! Accuracy below 85% threshold.")
    sys.exit(1)

print("✅ Evaluation passed!")

# 运行评估并等待所有结果
results = client.evaluate(
    target,
    data=dataset,
    evaluators=[evaluator],
    blocking=True  # 等待所有评估完成
)

# 评估完成后处理所有结果
for result in results:
    print("Input:", result["run"].inputs)
    print("Output:", result["run"].outputs)

    # 访问单个评估结果
    for eval_result in result["evaluation_results"]["results"]:
        print(f"  {eval_result.key}: {eval_result.score}")