可观测性快速入门

本教程将向您展示如何将应用程序追踪到 LangSmith，从而帮助您快速上手我们的可观测性 SDK。

如果您已经熟悉可观测性 SDK，或者不仅对 LLM 调用追踪感兴趣，您可以跳到下一步部分，或者查看操作指南。

追踪 LangChain 或 LangGraph 应用程序

如果您正在使用 LangChain 或 LangGraph（两者均与 LangSmith 无缝集成），您可以通过阅读LangChain 追踪指南或LangGraph 追踪指南来开始。

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。然后点击创建 API 密钥。

3. 设置环境

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. 定义您的应用程序

本教程将以一个简单的 RAG 应用程序为例进行讲解，但如果您愿意，也可以使用自己的代码——只需确保其中包含 LLM 调用即可！

应用程序代码

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

您可能想要追踪的第一件事就是所有的 OpenAI 调用。LangSmith 通过 wrap_openai (Python) 或 wrapOpenAI (TypeScript) 包装器使其变得简单。您只需修改代码以使用包装后的客户端，而不是直接使用 OpenAI 客户端。

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，当您如下调用您的应用程序时

rag("where did harrison work")

这将在 LangSmith 的默认追踪项目中生成一个仅包含 OpenAI 调用的追踪。它看起来应该像这样。

6. 追踪整个应用程序

您还可以使用 traceable 装饰器（Python 或 TypeScript）来追踪整个应用程序，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，如果您如下调用您的应用程序时

rag("where did harrison work")

这会生成一个仅包含整个流水线（OpenAI 调用作为子运行）的追踪——它看起来应该像这样

下一步

恭喜！如果您已完成这些步骤，您离成为 LangSmith 可观测性专家不远了。以下是一些您可能想要探索的后续主题

• 追踪多轮对话
• 将追踪发送到特定项目
• 在项目中筛选追踪

或者您可以访问操作指南页面，了解 LangSmith 可观测性可以实现的所有功能。

如果您喜欢视频教程，请查看 LangSmith 入门课程中的追踪基础视频。