跳到主要内容
Open on GitHub

Langfuse 🪢

什么是 Langfuse？ Langfuse 是一个开源的 LLM 工程平台，可帮助团队追踪 API 调用、监控性能并调试其 AI 应用程序中的问题。

追踪 LangChain​

Langfuse 追踪通过 Langchain 回调（Python, JS）与 Langchain 集成。因此，Langfuse SDK 会自动为您的 Langchain 应用程序的每次运行创建一个嵌套追踪。这使您能够记录、分析和调试您的 LangChain 应用程序。

您可以通过 (1) 构造函数参数 或 (2) 环境变量 配置集成。通过在 cloud.langfuse.com 注册或 自托管 Langfuse 获取您的 Langfuse 凭据。

构造函数参数​

pip install langfuse
from langfuse import Langfuse, get_client
from langfuse.langchain import CallbackHandler
from langchain_openai import ChatOpenAI  # Example LLM
from langchain_core.prompts import ChatPromptTemplate
 
# Initialize Langfuse client with constructor arguments
Langfuse(
    public_key="your-public-key",
    secret_key="your-secret-key",
    host="https://cloud.langfuse.com"  # Optional: defaults to https://cloud.langfuse.com
)
 
# Get the configured client instance
langfuse = get_client()
 
# Initialize the Langfuse handler
langfuse_handler = CallbackHandler()
 
# Create your LangChain components
llm = ChatOpenAI(model_name="gpt-4o")
prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}")
chain = prompt | llm
 
# Run your chain with Langfuse tracing
response = chain.invoke({"topic": "cats"}, config={"callbacks": [langfuse_handler]})
print(response.content)
 
# Flush events to Langfuse in short-lived applications
langfuse.flush()

环境变量​

LANGFUSE_SECRET_KEY="sk-lf-..."
LANGFUSE_PUBLIC_KEY="pk-lf-..."
# 🇪🇺 EU region
LANGFUSE_HOST="https://cloud.langfuse.com"
# 🇺🇸 US region
# LANGFUSE_HOST="https://us.cloud.langfuse.com"
# Initialize Langfuse handler
from langfuse.langchain import CallbackHandler
langfuse_handler = CallbackHandler()
 
# Your Langchain code
 
# Add Langfuse handler as callback (classic and LCEL)
chain.invoke({"input": "<user_input>"}, config={"callbacks": [langfuse_handler]})

要了解如何将此集成与其他 Langfuse 功能一起使用，请查看此端到端示例。

追踪 LangGraph​

本部分演示了 Langfuse 如何使用 LangChain 集成帮助调试、分析和迭代您的 LangGraph 应用程序。

初始化 Langfuse​

注意：您需要运行至少 Python 3.11 版本 (GitHub Issue)。

使用 Langfuse UI 中项目设置中的 API 密钥初始化 Langfuse 客户端，并将其添加到您的环境中。

%pip install langfuse
%pip install langchain langgraph langchain_openai langchain_community
import os

# get keys for your project from https://cloud.langfuse.com
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-***"
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-***"
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # for EU data region
# os.environ["LANGFUSE_HOST"] = "https://us.cloud.langfuse.com" # for US data region

# your openai key
os.environ["OPENAI_API_KEY"] = "***"

使用 LangGraph 构建简单聊天应用​

本节我们将要做的事情

  • 在 LangGraph 中构建一个可以回答常见问题的支持聊天机器人
  • 使用 Langfuse 追踪聊天机器人的输入和输出

我们将从一个基本的聊天机器人开始，并在下一节中构建一个更高级的多代理设置，同时介绍关键的 LangGraph 概念。

创建代理​

首先创建一个 StateGraph。StateGraph 对象将我们的聊天机器人结构定义为一个状态机。我们将添加节点来表示 LLM 和聊天机器人可以调用的函数，并添加边来指定机器人如何在这些函数之间转换。

from typing import Annotated

from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
from typing_extensions import TypedDict

from langgraph.graph import StateGraph
from langgraph.graph.message import add_messages

class State(TypedDict):
    # Messages have the type "list". The `add_messages` function in the annotation defines how this state key should be updated
    # (in this case, it appends messages to the list, rather than overwriting them)
    messages: Annotated[list, add_messages]

graph_builder = StateGraph(State)

llm = ChatOpenAI(model = "gpt-4o", temperature = 0.2)

# The chatbot node function takes the current State as input and returns an updated messages list. This is the basic pattern for all LangGraph node functions.
def chatbot(state: State):
    return {"messages": [llm.invoke(state["messages"])]}

# Add a "chatbot" node. Nodes represent units of work. They are typically regular python functions.
graph_builder.add_node("chatbot", chatbot)

# Add an entry point. This tells our graph where to start its work each time we run it.
graph_builder.set_entry_point("chatbot")

# Set a finish point. This instructs the graph "any time this node is run, you can exit."
graph_builder.set_finish_point("chatbot")

# To be able to run our graph, call "compile()" on the graph builder. This creates a "CompiledGraph" we can use invoke on our state.
graph = graph_builder.compile()

将 Langfuse 添加为调用的回调​

现在，我们将添加 LangChain 的 Langfuse 回调处理程序来追踪我们应用程序的步骤：config={"callbacks": [langfuse_handler]}

from langfuse.langchain import CallbackHandler

# Initialize Langfuse CallbackHandler for Langchain (tracing)
langfuse_handler = CallbackHandler()

for s in graph.stream({"messages": [HumanMessage(content = "What is Langfuse?")]},
                      config={"callbacks": [langfuse_handler]}):
    print(s)
{'chatbot': {'messages': [AIMessage(content='Langfuse is a tool designed to help developers monitor and observe the performance of their Large Language Model (LLM) applications. It provides detailed insights into how these applications are functioning, allowing for better debugging, optimization, and overall management. Langfuse offers features such as tracking key metrics, visualizing data, and identifying potential issues in real-time, making it easier for developers to maintain and improve their LLM-based solutions.', response_metadata={'token_usage': {'completion_tokens': 86, 'prompt_tokens': 13, 'total_tokens': 99}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_400f27fa1f', 'finish_reason': 'stop', 'logprobs': None}, id='run-9a0c97cb-ccfe-463e-902c-5a5900b796b4-0', usage_metadata={'input_tokens': 13, 'output_tokens': 86, 'total_tokens': 99})]}}

在 Langfuse 中查看追踪​

Langfuse 中的追踪示例：https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/d109e148-d188-4d6e-823f-aac0864afbab

Trace view of chat app in Langfuse