Building Your First AI Agent with LangChain

Prerequisites

• Python 3.9+
• An OpenAI or Anthropic API key
• Basic Python knowledge

Setup

pip install langchain langchain-openai

Step 1: Define Your Tools

Tools are functions your agent can call:

from langchain.tools import tool

@tool
def search_web(query: str) -> str:
    """Search the web for information."""
    # Implementation here
    return results

@tool
def calculate(expression: str) -> str:
    """Evaluate a math expression."""
    return str(eval(expression))

Step 2: Configure the Agent

from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent

llm = ChatOpenAI(model="gpt-4o")
agent = create_tool_calling_agent(llm, tools, prompt)

Step 3: Run the Agent

from langchain.agents import AgentExecutor

executor = AgentExecutor(agent=agent, tools=tools)
result = executor.invoke({"input": "What is the weather?"})

Next Steps

• Add memory for conversation persistence
• Implement error handling
• Add more sophisticated tools
• Deploy as an API endpoint