> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 如何在实验中重试失败的运行（仅限 Python）

在对大型[数据集](/langsmith/evaluation-concepts#datasets)运行[评估](/langsmith/evaluation-concepts#evaluation-lifecycle)时，可能会因速率限制、网络问题或其他瞬时错误导致一小部分示例失败。与其重新运行整个评估，不如在[实验](/langsmith/evaluation-concepts#experiment)中仅识别并重试失败的示例。

本指南展示了一种在评估工作流中构建重试逻辑的方法，并仅重试失败的示例。您可以使用 `error_handling='ignore'` 参数来跳过记录出错的运行，然后在 Python 中自动识别不成功的示例并重新运行它们。

## 步骤 1. 运行初始评估

运行初始评估，忽略错误以防止出错的运行被记录：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langsmith import Client

client = Client()

# 运行初始评估，忽略错误
# error_handling='ignore' 防止出错的运行被记录
results = await client.aevaluate(
    target,
    data="dataset",
    evaluators=[your_evaluators],
    error_handling='ignore'
)
```

## 步骤 2. 重试失败的示例并记录到同一实验

获取所有不成功的示例：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 识别不成功的示例
runs = client.list_runs(project_name=results.experiment_name)
successful_example_ids = [r.reference_example_id for r in runs]
unsuccessful_examples = (e for e in client.list_examples(dataset_name="dataset") if e.id not in successful_examples)
```

接下来，重新运行所有失败的示例并将它们记录到同一实验：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 仅重试失败的示例，并记录
results_retry = await client.aevaluate(
    target,
    unsuccessful_examples,
    evaluators=[your_evaluators],
    experiment=results.experiment_name,
    error_handling='ignore'
)
```

## 相关主题

* [运行评估](/langsmith/evaluate-llm-application)
* [异步运行评估](/langsmith/evaluation-async)
* [处理模型速率限制](/langsmith/rate-limiting)
* [实验配置](/langsmith/experiment-configuration)
* [评估现有实验](/langsmith/evaluate-existing-experiment)

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\langsmith\evaluate-with-retry.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>