07 Oct LangGraph Setup: Install LangGraph and Create Your Project

Before building bigger graphs, let’s set up a clean workspace to set up LangGraph. This takes about 10 minutes.

What you need

• Python 3.10 or higher (check with python –version)
• A code editor (VS Code works well)
• An API key from an LLM provider (needed from Chapter 8; you can skip it for now)

Step 1: Create a project folder and virtual environment

A virtual environment keeps this project’s libraries separate from the rest of your system.

mkdir langgraph-tutorial
cd langgraph-tutorial

python -m venv venv

Activate it:

# Windows
venv\Scripts\activate

# macOS / Linux
source venv/bin/activate

You will see (venv) at the start of your terminal line when it is active.

Step 2: Install the libraries

pip install -U langgraph python-dotenv

• langgraph is the main library
• python-dotenv loads secret keys from a file, so they never appear in your code

For the AI chapters, also install one model package:

# Option A: OpenAI
pip install -U langchain-openai

# Option B: Anthropic (Claude)
pip install -U langchain-anthropic

Step 3: Verify the installation

Run this in the terminal:

pip show langgraph

If you see a name and version number, you are set. You can also run the Chapter 1 example as a quick test.

Step 4: Store your API key safely

Create a file named .env in your project folder:

OPENAI_API_KEY=your-key-here

For Anthropic, use ANTHROPIC_API_KEY=your-key-here instead.

Load it in Python:

from dotenv import load_dotenv
import os

load_dotenv()
print("Key loaded:", os.getenv("OPENAI_API_KEY") is not None)

Output:

Key loaded: True

Important: never paste API keys directly into your code, and never upload .env to GitHub. Create a .gitignore file containing:

.env
venv/
__pycache__/

Step 5: Recommended project structure

langgraph-tutorial/
├── venv/
├── .env
├── .gitignore
├── requirements.txt
├── ch01_hello.py
├── ch02_state_nodes_edges.py
└── ch03_setup_check.py

One file per chapter keeps things easy to find. Save your dependencies with:

pip freeze > requirements.txt

Anyone can then recreate your setup with pip install -r requirements.txt.

Step 6: See your graph as a diagram

LangGraph can draw your graph. Add this to the end of your Chapter 2 code:

print(graph.get_graph().draw_mermaid())

Output (Mermaid text):

graph TD;
    __start__ --> clean_question;
    clean_question --> make_answer;
    make_answer --> __end__;

Paste this text into a Mermaid viewer (for example, mermaid.live) to see the flowchart. We will explore visualization more in Chapter 20.

Common setup problems

• ModuleNotFoundError: langgraph: activate your venv, then reinstall
• python not found: try python3 instead
• Key shows None: check the .env file name and location, and that you called load_dotenv()
• Old Python version: install Python 3.10 or newer from python.org

Summary

• Use a virtual environment for every project
• Install langgraph, python-dotenv, and one model package
• Keep API keys in .env, and keep .env out of Git
• get_graph().draw_mermaid() gives you a diagram of any graph

Practice

1. Create the project folder, virtual environment, and .gitignore
2. Run the Chapter 2 example inside your new setup and print its Mermaid diagram

---

If you liked the tutorial, spread the word and share the link and our website, Studyopedia, with others.

---

For Videos, Join Our YouTube Channel: Join Now

---

Read More:

• Generative AI Tutorial
• AI Ethics
• Machine Learning Tutorial
• Deep Learning Tutorial
• Ollama Tutorial
• Retrieval Augmented Generation (RAG) Tutorial
• ChatGPT Tutorial
• Microsoft Copilot Tutorial