跳到主要内容
Open on GitHub

LLMonitor

LLMonitor 是一个开源的可观测性平台,提供成本和使用情况分析、用户追踪、跟踪和评估工具。

设置

llmonitor.com 上创建一个账户,然后复制您新应用的 tracking id

获取后,通过运行以下命令将其设置为环境变量:

export LLMONITOR_APP_ID="..."

如果您不想设置环境变量,可以在初始化回调处理器时直接传递密钥:

from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler

handler = LLMonitorCallbackHandler(app_id="...")

与 LLM/聊天模型一起使用

from langchain_openai import OpenAI
from langchain_openai import ChatOpenAI

handler = LLMonitorCallbackHandler()

llm = OpenAI(
callbacks=[handler],
)

chat = ChatOpenAI(callbacks=[handler])

llm("Tell me a joke")

API 参考:OpenAI | ChatOpenAI

与链和代理一起使用

请务必将回调处理器传递给 run 方法,以便正确跟踪所有相关的链和 LLM 调用。

还建议在元数据中传递 agent_name,以便在仪表板中区分不同的代理。

示例

from langchain_openai import ChatOpenAI
from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler
from langchain_core.messages import SystemMessage, HumanMessage
from langchain.agents import OpenAIFunctionsAgent, AgentExecutor, tool

llm = ChatOpenAI(temperature=0)

handler = LLMonitorCallbackHandler()

@tool
def get_word_length(word: str) -> int:
"""Returns the length of a word."""
return len(word)

tools = [get_word_length]

prompt = OpenAIFunctionsAgent.create_prompt(
system_message=SystemMessage(
content="You are very powerful assistant, but bad at calculating lengths of words."
)
)

agent = OpenAIFunctionsAgent(llm=llm, tools=tools, prompt=prompt, verbose=True)
agent_executor = AgentExecutor(
agent=agent, tools=tools, verbose=True, metadata={"agent_name": "WordCount"} # <- recommended, assign a custom name
)
agent_executor.run("how many letters in the word educa?", callbacks=[handler])

另一个示例

import os

from langchain_community.agent_toolkits.load_tools import load_tools
from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

os.environ["LLMONITOR_APP_ID"] = ""
os.environ["OPENAI_API_KEY"] = ""
os.environ["SERPAPI_API_KEY"] = ""

handler = LLMonitorCallbackHandler()
llm = ChatOpenAI(temperature=0, callbacks=[handler])
tools = load_tools(["serpapi", "llm-math"], llm=llm)
agent = create_react_agent("openai:gpt-4.1-mini", tools)

input_message = {
"role": "user",
"content": "What's the weather in SF?",
}

agent.invoke({"messages": [input_message]})

用户追踪

用户追踪允许您识别用户、跟踪他们的成本、对话等。

from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler, identify

with identify("user-123"):
llm.invoke("Tell me a joke")

with identify("user-456", user_props={"email": "user456@test.com"}):
agent.invoke(...)

支持

对于集成方面的任何问题,您可以通过 Discord电子邮件 联系 LLMonitor 团队。