Observability 快速入门

本教程将通过演示如何将你的应用程序追踪到 LangSmith，帮助你快速开始使用我们的 observability SDK。

如果你已经熟悉 observability SDK，或者对追踪不仅仅是 LLM 调用感兴趣，你可以跳到后续步骤部分，或者查看操作指南。

追踪 LangChain 或 LangGraph 应用

如果你正在使用 LangChain 或 LangGraph，它们都与 LangSmith 无缝集成，你可以通过阅读关于使用 LangChain 进行追踪或使用 LangGraph 进行追踪的指南来开始使用。

1. 安装依赖

Python

pip install -U langsmith openai

TypeScript

yarn add langsmith openai

2. 创建 API 密钥

要创建 API 密钥，请前往 LangSmith 设置页面。然后点击 Create API Key（创建 API 密钥）。

3. 设置你的环境

Shell

export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY="<your-langsmith-api-key>"
# The example uses OpenAI, but it's not necessary if your code uses another LLM provider
export OPENAI_API_KEY="<your-openai-api-key>"

4. 定义你的应用

在本教程中，我们将instrument一个简单的 RAG 应用，但如果你愿意，可以随意使用你自己的代码 - 只要确保它有 LLM 调用！

应用代码

Python

from openai import OpenAI

openai_client = OpenAI()

# This is the retriever we will use in RAG
# This is mocked out, but it could be anything we want
def retriever(query: str):
    results = ["Harrison worked at Kensho"]
    return results

# This is the end-to-end RAG chain.
# It does a retrieval step then calls OpenAI
def rag(question):
    docs = retriever(question)
    system_message = """Answer the users question using only the provided information below:
    
    {docs}""".format(docs="\n".join(docs))
    
    return openai_client.chat.completions.create(
        messages=[
            {"role": "system", "content": system_message},
            {"role": "user", "content": question},
        ],
        model="gpt-4o-mini",
    )

TypeScript

import { OpenAI } from "openai";

const openAIClient = new OpenAI();

// This is the retriever we will use in RAG
// This is mocked out, but it could be anything we want
async function retriever(query: string) {
  return ["This is a document"];
}

// This is the end-to-end RAG chain.
// It does a retrieval step then calls OpenAI
async function rag(question: string) {
  const docs = await retriever(question);
  
  const systemMessage =
    "Answer the users question using only the provided information below:\n\n" +
    docs.join("\n");
    
  return await openAIClient.chat.completions.create({
    messages: [
      { role: "system", content: systemMessage },
      { role: "user", content: question },
    ],
    model: "gpt-4o-mini",
  });
}

5. 追踪 OpenAI 调用

你可能想要追踪的第一件事是所有 OpenAI 调用。LangSmith 通过 wrap_openai (Python) 或 wrapOpenAI (TypeScript) wrappers 使这变得容易。你所要做的就是修改你的代码以使用 wrapped client，而不是直接使用 OpenAI client。

Python

from openai import OpenAI
from langsmith.wrappers import wrap_openai

openai_client = wrap_openai(OpenAI())

# This is the retriever we will use in RAG
# This is mocked out, but it could be anything we want
def retriever(query: str):
    results = ["Harrison worked at Kensho"]
    return results

# This is the end-to-end RAG chain.
# It does a retrieval step then calls OpenAI
def rag(question):
    docs = retriever(question)
    system_message = """Answer the users question using only the provided information below:
    
    {docs}""".format(docs="\n".join(docs))
    
    return openai_client.chat.completions.create(
        messages=[
            {"role": "system", "content": system_message},
            {"role": "user", "content": question},
        ],
        model="gpt-4o-mini",
    )

TypeScript

import { OpenAI } from "openai";
import { wrapOpenAI } from "langsmith/wrappers";

const openAIClient = wrapOpenAI(new OpenAI());

// This is the retriever we will use in RAG
// This is mocked out, but it could be anything we want
async function retriever(query: string) {
  return ["This is a document"];
}

// This is the end-to-end RAG chain.
// It does a retrieval step then calls OpenAI
async function rag(question: string) {
  const docs = await retriever(question);
  
  const systemMessage =
    "Answer the users question using only the provided information below:\n\n" +
    docs.join("\n");
    
  return await openAIClient.chat.completions.create({
    messages: [
      { role: "system", content: systemMessage },
      { role: "user", content: question },
    ],
    model: "gpt-4o-mini",
  });
}

现在，当你如下调用你的应用程序时

rag("where did harrison work")

这将在 LangSmith 的默认追踪项目中生成仅包含 OpenAI 调用的追踪。它应该看起来像这样。

6. 追踪整个应用

你还可以使用 [traceable] 装饰器 (Python 或 TypeScript) 来追踪你的整个应用，而不仅仅是 LLM 调用。

Python

from openai import OpenAI
from langsmith import traceable
from langsmith.wrappers import wrap_openai

openai_client = wrap_openai(OpenAI())

def retriever(query: str):
    results = ["Harrison worked at Kensho"]
    return results

@traceable
def rag(question):
    docs = retriever(question)
    system_message = """Answer the users question using only the provided information below:
    
    {docs}""".format(docs="\n".join(docs))
    
    return openai_client.chat.completions.create(
        messages=[
            {"role": "system", "content": system_message},
            {"role": "user", "content": question},
        ],
        model="gpt-4o-mini",
    )

TypeScript

import { OpenAI } from "openai";
import { traceable } from "langsmith/traceable";
import { wrapOpenAI } from "langsmith/wrappers";

const openAIClient = wrapOpenAI(new OpenAI());

async function retriever(query: string) {
  return ["This is a document"];
}

const rag = traceable(async function rag(question: string) {
  const docs = await retriever(question);
  
  const systemMessage =
    "Answer the users question using only the provided information below:\n\n" +
    docs.join("\n");
    
  return await openAIClient.chat.completions.create({
    messages: [
      { role: "system", content: systemMessage },
      { role: "user", content: question },
    ],
    model: "gpt-4o-mini",
  });
});

现在，如果你如下调用你的应用程序

rag("where did harrison work")

这将生成仅包含整个 pipeline 的追踪（OpenAI 调用作为子运行）- 它应该看起来像这样

后续步骤

恭喜你！如果你已经走到这一步，那么你离成为 LangSmith observability 专家已经不远了。以下是你可能想要接下来探索的一些主题

• 追踪多轮对话
• 将追踪发送到特定项目
• 在项目中筛选追踪

或者你可以访问操作指南页面，了解关于你可以使用 LangSmith observability 做的一切。

如果你更喜欢视频教程，请查看 LangSmith 入门课程中的Tracing Basics 视频。