Skip to main content
Aim 让可视化和调试 LangChain 执行过程变得极为简便。Aim 可追踪 LLM 和工具的输入输出，以及 Agent 的行为。 使用 Aim，您可以轻松调试和检查单次执行： 227784778 06b806c7 74a1 4d15 ab85 9ece09b458aa 此外，您还可以并排比较多次执行： 227784994 699b24b7 e69b 48f9 9ffa e6a6142fd719 Aim 完全开源，了解更多。 让我们继续了解如何启用和配置 Aim 回调。

​
使用 Aim 追踪 LangChain 执行

本 notebook 将探索三种使用场景。首先，我们将安装必要的包并导入相关模块，然后配置两个可在 Python 脚本或终端中设置的环境变量。 
pip install -qU  aim
pip install -qU  langchain
pip install -qU  langchain-openai
pip install -qU  google-search-results

import os
from datetime import datetime

from langchain_community.callbacks import AimCallbackHandler
from langchain_core.callbacks import StdOutCallbackHandler
from langchain_openai import OpenAI
示例中使用 GPT 模型作为 LLM，OpenAI 提供了相应的 API。您可以从以下链接获取密钥：platform.openai.com/account/api-keys。 我们将使用 SerpApi 从 Google 获取搜索结果。请访问 serpapi.com/manage-api-key 获取 SerpApi 密钥。 
os.environ["OPENAI_API_KEY"] = "..."
os.environ["SERPAPI_API_KEY"] = "..."
AimCallbackHandler 的事件方法接受 LangChain 模块或 Agent 作为输入，并将至少包含提示和生成结果，以及 LangChain 模块的序列化版本记录到指定的 Aim 运行中。 
session_group = datetime.now().strftime("%m.%d.%Y_%H.%M.%S")
aim_callback = AimCallbackHandler(
    repo=".",
    experiment_name="scenario 1: OpenAI LLM",
)

callbacks = [StdOutCallbackHandler(), aim_callback]
llm = OpenAI(temperature=0, callbacks=callbacks)
flush_tracker 函数用于将 LangChain 资产记录到 Aim。默认情况下，会话将被重置而非直接终止。

场景一

第一个场景中，我们将使用 OpenAI LLM。 
# scenario 1 - LLM
llm_result = llm.generate(["Tell me a joke", "Tell me a poem"] * 3)
aim_callback.flush_tracker(
    langchain_asset=llm,
    experiment_name="scenario 2: Chain with multiple SubChains on multiple generations",
)

场景二

场景二涉及跨多轮生成使用包含多个子链的链式结构。 
from langchain_classic.chains import LLMChain
from langchain_core.prompts import PromptTemplate

# scenario 2 - Chain
template = """You are a playwright. Given the title of play, it is your job to write a synopsis for that title.
Title: {title}
Playwright: This is a synopsis for the above play:"""
prompt_template = PromptTemplate(input_variables=["title"], template=template)
synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callbacks=callbacks)

test_prompts = [
    {
        "title": "documentary about good video games that push the boundary of game design"
    },
    {"title": "the phenomenon behind the remarkable speed of cheetahs"},
    {"title": "the best in class mlops tooling"},
]
synopsis_chain.apply(test_prompts)
aim_callback.flush_tracker(
    langchain_asset=synopsis_chain, experiment_name="scenario 3: Agent with Tools"
)

场景三

第三个场景涉及带有工具的 Agent。 
from langchain.agents import create_agent, load_tools

# scenario 3 - Agent with Tools
tools = load_tools(["serpapi", "llm-math"], llm=llm, callbacks=callbacks)

agent = create_agent(
    model=llm,
    tools=tools,
    callbacks=callbacks,
)

agent.invoke(
    "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
)

aim_callback.flush_tracker(langchain_asset=agent, reset=False, finish=True)

> Entering new AgentExecutor chain...
 I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.
Action: Search
Action Input: "Leo DiCaprio girlfriend"
Observation: Leonardo DiCaprio seemed to prove a long-held theory about his love life right after splitting from girlfriend Camila Morrone just months ...
Thought: I need to find out Camila Morrone's age
Action: Search
Action Input: "Camila Morrone age"
Observation: 25 years
Thought: I need to calculate 25 raised to the 0.43 power
Action: Calculator
Action Input: 25^0.43
Observation: Answer: 3.991298452658078

Thought: I now know the final answer
Final Answer: Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.

> Finished chain.
在 GitHub 上编辑此页面 或 提交问题。
通过 MCP 将这些文档接入 Claude、VSCode 等工具，获取实时解答。