AI Agents with LangChain & Autonomous Workflows · 课时

构建您的第一个简单智能体

按照分步指南设置环境，并使用 LangChain 构建一个基础人工智能代理。

构建您的第一个简单智能体 是 CoddyKit 上的免费 AI Agents with LangChain & Autonomous Workflows 课时。这是第 3 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 AI Agents with LangChain & Autonomous Workflows 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 AI Agents with LangChain & Autonomous Workflows 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

Build Your First Agent!

Time to build your first AI agent with LangChain — connecting an LLM to basic tools so it can answer your queries intelligently.

Set Up Your Python Environment

First, set up Python 3.9+ and a virtual environment to isolate dependencies. Create one with venv, then activate it before you install anything.

Install LangChain & Dependencies

Now install LangChain and the OpenAI integration. Run the pip command inside your activated virtual environment.

Connect to an LLM

Your agent needs a brain. Initialize ChatOpenAI with your API key stored as the OPENAI_API_KEY environment variable — never hardcode it.

import os
from langchain_openai import ChatOpenAI

def main():
    # In a real setup, ensure OPENAI_API_KEY is set
    # For demonstration, we'll assume it's available
    # os.environ["OPENAI_API_KEY"] = "sk-..." # DON'T hardcode!

    try:
        llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
        print("LLM initialized successfully!")
        # You can test it:
        # response = llm.invoke("Hello, LLM!")
        # print(response.content)
    except Exception as e:
        print(f"Error initializing LLM: {e}")
        print("Please ensure OPENAI_API_KEY is set.")

if __name__ == "__main__":
    main()

Agents Need Tools

An agent is an LLM plus tools — functions or APIs that let it act on the world: search, run code, calculate. Here we give ours a calculator.

import os
from langchain_openai import ChatOpenAI
from langchain.tools import Tool
from langchain_community.utilities import LLMMathChain

def main():
    # Ensure OPENAI_API_KEY is set
    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)

    # Create a basic math tool
    llm_math_chain = LLMMathChain.from_llm(llm)
    math_tool = Tool.from_function(
        func=llm_math_chain.run,
        name="Calculator",
        description="Useful for when you need to answer questions about math."
    )
    tools = [math_tool]
    print("Basic math tool created and ready!")

if __name__ == "__main__":
    main()

Choosing Your Agent Type

The agent type defines how it reasons. We'll use create_react_agent — ReAct means Reason and Act: it plans, observes results, then refines.

Combining Components

Now combine the pieces: create_react_agent takes your LLM, tools, and prompt to build the logic, then AgentExecutor wraps it to make it runnable.

import os
from langchain_openai import ChatOpenAI
from langchain.tools import Tool
from langchain_community.utilities import LLMMathChain
from langchain.agents import AgentExecutor, create_react_agent
from langchain_core.prompts import ChatPromptTemplate

def main():
    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
    llm_math_chain = LLMMathChain.from_llm(llm)
    math_tool = Tool.from_function(
        func=llm_math_chain.run,
        name="Calculator",
        description="Useful for when you need to answer questions about math."
    )
    tools = [math_tool]

    # Define the prompt for the agent
    prompt = ChatPromptTemplate.from_messages([
        ("system", "You are a helpful AI assistant. Use tools when necessary."),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}")
    ])

    # Create the agent
    agent = create_react_agent(llm, tools, prompt)

    # Create the agent executor
    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
    print("Agent assembled and ready for action!")

if __name__ == "__main__":
    main()

Asking Your Agent a Question

With the agent assembled, give it a task via invoke. Ask a math question and watch it reach for its calculator tool to answer.

import os
from langchain_openai import ChatOpenAI
from langchain.tools import Tool
from langchain_community.utilities import LLMMathChain
from langchain.agents import AgentExecutor, create_react_agent
from langchain_core.prompts import ChatPromptTemplate

def main():
    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
    llm_math_chain = LLMMathChain.from_llm(llm)
    math_tool = Tool.from_function(
        func=llm_math_chain.run,
        name="Calculator",
        description="Useful for when you need to answer questions about math."
    )
    tools = [math_tool]

    prompt = ChatPromptTemplate.from_messages([
        ("system", "You are a helpful AI assistant. Use tools when necessary."),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}")
    ])

    agent = create_react_agent(llm, tools, prompt)
    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

    print("Asking the agent: 'What is 123 multiplied by 456?'")
    response = agent_executor.invoke({"input": "What is 123 multiplied by 456?"})
    print("\nAgent's final answer:")
    print(response["output"])

if __name__ == "__main__":
    main()

Understanding the Agent's Response

With verbose=True you see the agent's thought process: Thought, Action, Action Input, Observation, then Final Answer. That transparency is key to debugging.

Your Complete First Agent!

Here's your complete first agent. Set your API key, run it, and try changing the input question to see it reason through different problems.

import os
from langchain_openai import ChatOpenAI
from langchain.tools import Tool
from langchain_community.utilities import LLMMathChain
from langchain.agents import AgentExecutor, create_react_agent
from langchain_core.prompts import ChatPromptTemplate

def main():
    # 1. Set up your LLM
    # Ensure OPENAI_API_KEY is set as an environment variable
    # os.environ["OPENAI_API_KEY"] = "YOUR_KEY_HERE" # DO NOT hardcode!
    try:
        llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
    except Exception as e:
        print(f"Error: {e}. Please ensure OPENAI_API_KEY is set.")
        return

    # 2. Define your tools
    llm_math_chain = LLMMathChain.from_llm(llm)
    math_tool = Tool.from_function(
        func=llm_math_chain.run,
        name="Calculator",
        description="Useful for when you need to answer questions about math."
    )
    tools = [math_tool]

    # 3. Define the agent's prompt
    prompt = ChatPromptTemplate.from_messages([
        ("system", "You are a helpful AI assistant. Use tools when necessary."),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}")
    ])

    # 4. Create the agent
    agent = create_react_agent(llm, tools, prompt)

    # 5. Create the AgentExecutor
    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

    # 6. Run the agent
    print("\n--- Running the Agent ---")
    question = "What is the square root of 144 plus 25?"
    print(f"Agent input: '{question}'")
    response = agent_executor.invoke({"input": question})
    print("\n--- Agent's Final Answer ---")
    print(response["output"])

if __name__ == "__main__":
    main()

Agent Components Check

You've seen how to build a basic agent. Which of the following are essential components when constructing a LangChain agent using create_react_agent?

Recap: Your First Agent!

Recap: you built a real agent — set up the environment, connected an LLM, added a tool, assembled it with create_react_agent and AgentExecutor, and watched it think.

常见问题解答

「构建您的第一个简单智能体」课时是免费的吗？

是的 — 「构建您的第一个简单智能体」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 AI Agents with LangChain & Autonomous Workflows 课程的其余内容，请升级到 CoddyKit PRO。 AI Agents with LangChain & Autonomous Workflows 课程共包含 4 节课。

「构建您的第一个简单智能体」这节课中我会学到什么？

按照分步指南设置环境，并使用 LangChain 构建一个基础人工智能代理。你通过在浏览器中直接运行的动手代码来练习 AI Agents with LangChain & Autonomous Workflows，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 AI Agents with LangChain & Autonomous Workflows 需要有经验吗？

无需任何先前经验。CoddyKit 上的 AI Agents with LangChain & Autonomous Workflows 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 3 节课，共 4 节。

「构建您的第一个简单智能体」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 AI Agents with LangChain & Autonomous Workflows 课中编写并运行代码吗？

能。每节 AI Agents with LangChain & Autonomous Workflows 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 AI Agents with LangChain & Autonomous Workflows