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

# 如何评估可运行对象

<Info>
  * `langchain`: [Python](https://docs.langchain.com/oss/python/langchain/overview) 和 [JS/TS](https://docs.langchain.com/oss/javascript/langchain/overview)
  * 可运行对象: [Python](https://reference.langchain.com/python/langchain_core/runnables/) 和 [JS/TS](https://reference.langchain.com/javascript/classes/_langchain_core.runnables.Runnable.html)
</Info>

`langchain` 的 [`Runnable`](https://reference.langchain.com/python/langchain_core/runnables/) 对象（例如聊天模型、检索器、链等）可以直接传递给 `evaluate()` / `aevaluate()`。

## 设置

让我们定义一个简单的链来进行评估。首先，安装所有必需的包：

<CodeGroup>
  ```bash Python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install -U langsmith langchain[openai]
  ```

  ```bash TypeScript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add langsmith @langchain/openai
  ```
</CodeGroup>

现在定义一个链：

<CodeGroup>
  ```python Python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  from langchain.chat_models import init_chat_model
  from langchain_core.output_parsers import StrOutputParser
  from langchain_core.prompts import ChatPromptTemplate

  instructions = (
      "Please review the user query below and determine if it contains any form "
      "of toxic behavior, such as insults, threats, or highly negative comments. "
      "Respond with 'Toxic' if it does, and 'Not toxic' if it doesn't."
  )

  prompt = ChatPromptTemplate(
      [("system", instructions), ("user", "{text}")],
  )

  model = init_chat_model("gpt-5.4")
  chain = prompt | model | StrOutputParser()
  ```

  ```typescript TypeScript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import { ChatOpenAI } from "@langchain/openai";
  import { ChatPromptTemplate } from "@langchain/core/prompts";
  import { StringOutputParser } from "@langchain/core/output_parsers";

  const prompt = ChatPromptTemplate.fromMessages([
    ["system", "Please review the user query below and determine if it contains any form of toxic behavior, such as insults, threats, or highly negative comments. Respond with 'Toxic' if it does, and 'Not toxic' if it doesn't."],
    ["user", "{text}"]
  ]);

  const chatModel = new ChatOpenAI();
  const outputParser = new StringOutputParser();
  const chain = prompt.pipe(chatModel).pipe(outputParser);
  ```
</CodeGroup>

## 评估

要评估我们的链，可以直接将其传递给 `evaluate()` / `aevaluate()` 方法。请注意，链的输入变量必须与示例输入的键匹配。在这种情况下，示例输入应具有 `{"text": "..."}` 的形式。

<CodeGroup>
  ```python Python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import asyncio
  from langsmith import Client, aevaluate

  client = Client()

  # Clone a dataset of texts with toxicity labels.
  # Each example input has a "text" key and each output has a "label" key.
  dataset = client.clone_public_dataset(
      "https://smith.langchain.com/public/3d6831e6-1680-4c88-94df-618c8e01fc55/d"
  )

  def correct(outputs: dict, reference_outputs: dict) -> bool:
      # Since our chain outputs a string not a dict, this string
      # gets stored under the default "output" key in the outputs dict:
      actual = outputs["output"]
      expected = reference_outputs["label"]
      return actual == expected

  async def main():
      results = await aevaluate(
          chain,
          data=dataset,
          evaluators=[correct],
          experiment_prefix="gpt-5.4, baseline",
          metadata={"models": "openai:gpt-5.4"},  # optional, used to populate model/prompt/tool columns in UI
      )
      print(results)

  asyncio.run(main())
  ```

  ```typescript TypeScript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import { evaluate } from "langsmith/evaluation";
  import { Client } from "langsmith";

  const langsmith = new Client();

  const dataset = await client.clonePublicDataset(
    "https://smith.langchain.com/public/3d6831e6-1680-4c88-94df-618c8e01fc55/d"
  )

  await evaluate(chain, {
    data: dataset.name,
    evaluators: [correct],
    experimentPrefix: "gpt-5.4, baseline",
    metadata: { models: "openai:gpt-5.4" },  // optional, used to populate model/prompt/tool columns in UI
  });
  ```
</CodeGroup>

可运行对象会为每个输出进行适当的追踪。

<img src="https://mintcdn.com/other-405835d4/kU99RLuXybYOidw_/langsmith/images/runnable-eval.png?fit=max&auto=format&n=kU99RLuXybYOidw_&q=85&s=b2c016859220cf344daf7528337513d7" alt="可运行对象评估" width="1909" height="925" data-path="langsmith/images/runnable-eval.png" />

## 相关内容

* [如何评估 `langgraph` 图](/langsmith/evaluate-on-intermediate-steps)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档](/use-these-docs)通过 MCP 连接到 Claude、VSCode 等，以获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/langsmith/langchain-runnable.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>