LangChain Basics: Build Your First AI Agent

LangChain is the most-used framework for building LLM applications. This tutorial walks you through your first AI agent in 30 minutes.

What is LangChain?

LangChain is an open-source framework for building applications with large language models. It provides:

• Chains: Composable sequences of LLM calls
• Agents: LLMs that can use tools and make decisions
• Memory: State persistence across calls
• Retrieval: Connect LLMs to your own data

Install

pip install langchain langchain-openai
export OPENAI_API_KEY="sk-..."

Your first chain

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(model="gpt-4")
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant."),
    ("user", "{question}"),
])
chain = prompt | llm
response = chain.invoke({"question": "What is LangChain?"})
print(response.content)

Your first agent

from langchain.agents import create_react_agent
from langchain.tools import Tool

tools = [Tool(name="search", func=search.run, description="Web search")]
agent = create_react_agent(llm, tools)
agent.invoke({"input": "What's the weather in Beijing?"})

Key takeaways

• LangChain abstracts LLM calls into composable pieces
• Agents let LLMs choose tools dynamically
• Memory lets you build stateful applications