5个Lang：3-LangSmith简单实践

LangSmith与LangChain集成实践

原创于 2025-11-28 07:30:00 发布 · 339 阅读

9 ·

CC 4.0 BY-SA版权

文章标签：

#Langchain #Langgraph #LangServe #LangFuse #LangSmith

大模型应用同时被 3 个专栏收录

167 篇文章

订阅专栏

Langchain

22 篇文章

订阅专栏

LangGraph

12 篇文章

订阅专栏

今天介绍一个AI生产力工具：LangSmith。本篇文章主要在Tracing部分的实操，包括环境准备、如何将你的LangChain程序和LangSimth平台打通，如何使用LangSimth调试Prompt，以及如何进行在线数据标注和收集，为后面的自动化评估作准备。

在开始之前，我们先来了解下为什么要有LangSmith：

维护一个生产级的 LLM 应用，我们需要做什么？

各种指标监控与统计：访问记录、响应时长、Token用量、计费等等
调试 Prompt，Prompt 版本管理（便于升级/回滚）
测试/验证系统的相关评估指标
数据集管理（便于回归测试）

LangSimth平台帮助你快速、可视化完成上面的流程。它允许您调试、测试、评估和监控构建在任何LLM框架上的链和智能代理，并与LangChain无缝集成。

1. 环境准备

LangSmith是LangChain 官方的 SaaS 服务，现已开源。

平台入口：https://www.langchain.com/langsmith

文档地址：https://python.langchain.com/docs/langsmith/walkthrough

注册登录之后，需要生成API key

在这里插入图片描述

!pip install langchain langchain_openai

Requirement already satisfied: langchain in /usr/local/lib/python3.10/dist-packages (0.1.16)
Requirement already satisfied: langchain_openai in /usr/local/lib/python3.10/dist-packages (0.1.3)
Requirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)
Requirement already satisfied: SQLAlchemy<3,>=1.4 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.0.29)
Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.5)
Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (4.0.3)
Requirement already satisfied: dataclasses-json<0.7,>=0.5.7 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.6.4)
Requirement already satisfied: jsonpatch<2.0,>=1.33 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.33)
Requirement already satisfied: langchain-community<0.1,>=0.0.32 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.34)
Requirement already satisfied: langchain-core<0.2.0,>=0.1.42 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.46)
Requirement already satisfied: langchain-text-splitters<0.1,>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.1)
Requirement already satisfied: langsmith<0.2.0,>=0.1.17 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.51)
Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.25.2)
Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.7.0)
Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.31.0)
Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (8.2.3)
Requirement already satisfied: openai<2.0.0,>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from langchain_openai) (1.23.6)
Requirement already satisfied: tiktoken<1,>=0.5.2 in /usr/local/lib/python3.10/dist-packages (from langchain_openai) (0.6.0)
Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)
Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.2.0)
Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.4.1)
Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.5)
Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.4)
Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (3.21.1)
Requirement already satisfied: typing-inspect<1,>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (0.9.0)
Requirement already satisfied: jsonpointer>=1.9 in /usr/local/lib/python3.10/dist-packages (from jsonpatch<2.0,>=1.33->langchain) (2.4)
Requirement already satisfied: packaging<24.0,>=23.2 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2.0,>=0.1.42->langchain) (23.2)
Requirement already satisfied: orjson<4.0.0,>=3.9.14 in /usr/local/lib/python3.10/dist-packages (from langsmith<0.2.0,>=0.1.17->langchain) (3.10.1)
Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.10.0->langchain_openai) (3.7.1)
Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai<2.0.0,>=1.10.0->langchain_openai) (1.7.0)
Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.10.0->langchain_openai) (0.27.0)
Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.10.0->langchain_openai) (1.3.1)
Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.10.0->langchain_openai) (4.66.2)
Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai<2.0.0,>=1.10.0->langchain_openai) (4.11.0)
Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (0.6.0)
Requirement already satisfied: pydantic-core==2.18.1 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (2.18.1)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2.0.7)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2024.2.2)
Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.3)
Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken<1,>=0.5.2->langchain_openai) (2023.12.25)
Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai<2.0.0,>=1.10.0->langchain_openai) (1.2.1)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai<2.0.0,>=1.10.0->langchain_openai) (1.0.5)
Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->openai<2.0.0,>=1.10.0->langchain_openai) (0.14.0)
Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)

# 设置OpenAI KEY环境变量
import os
import getpass
os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')

OpenAI API Key:··········

2. 打通LangChain和LangSmith

要打通 LangChain 和 LangSmith 很简单，只需要在环境变量中加入如下4个信息：

import os
LANGCHAIN_API_KEY = "ls__xxxxxx"  # LangChain API Key
os.environ["LANGCHAIN_ENDPOINT"] = "https://api.smith.langchain.com"  #LangSmith的服务端点

os.environ["LANGCHAIN_TRACING_V2"]="true"
os.environ["LANGCHAIN_PROJECT"]="test-001" #自定义项目名称

示例代码：

from langchain_openai import ChatOpenAI
from langchain.prompts import PromptTemplate
from langchain.schema.output_parser import StrOutputParser
from langchain.schema.runnable import RunnablePassthrough
from langchain.schema import HumanMessage
from langchain.prompts.chat import HumanMessagePromptTemplate
from langchain.prompts import ChatPromptTemplate

model = ChatOpenAI()

prompt_template = """
我的名字叫【{name}】，我的个人介绍是【{description}】。
请根据我的名字和介绍，帮我想一段有吸引力的自我介绍的句子，以此来吸引读者关注和点赞我的账号。
"""
prompt = ChatPromptTemplate.from_messages([
    HumanMessagePromptTemplate.from_template(prompt_template)
])

# 定义输出解析器
parser = StrOutputParser()

chain = (
    prompt
    | model
    | parser
)

## invoke的第一个参数，传入json格式的参数，key与prompt中的参数名一致
response = chain.invoke({'name': 'Arron', 'description': '热爱AI，持续学习，持续干货输出'})
print(response)

"大家好，我是Arron，一个对AI充满热爱并持续学习的人。在这里，我会不断分享最新的干货内容，让我们一起探索AI的无限可能！期待与你们一起交流学习！"

在LangSmith中查看项目test-001，结果如下图所示：

在这里插入图片描述