Agentic-LangGraph

Hands-on LangGraph practice project with notebook-based workflows for building graph-driven agents, tool-calling chatbots, and LLM integrations.

Overview

This repository contains two Jupyter notebook modules:

• 01-LangGraph/simple.ipynb: A beginner LangGraph flow with conditional routing.
• 02-LangGraph/chatbot.ipynb: A tool-using chatbot workflow with Arxiv, Wikipedia, and Tavily search integrations.

The project demonstrates how to:

• Define graph state using TypedDict
• Add nodes and edges in StateGraph
• Build conditional branches and looping workflows
• Bind tools to an LLM
• Visualize graph topology with Mermaid PNG rendering

Project Structure

Agentic-LangGraph/
	01-LangGraph/
		simple.ipynb
	02-LangGraph/
		chatbot.ipynb
	requirements.txt
	README.md

Tech Stack

• Python
• LangGraph
• LangChain
• LangChain Community
• LangChain Groq
• Pydantic
• python-dotenv
• Arxiv and Wikipedia tool wrappers

Installation

1. Clone the repository

git clone https://github.com/supritR21/Agentic-LangGraph.git
cd Agentic-LangGraph

2. Create and activate virtual environment

Windows (PowerShell):

python -m venv .venv
.\.venv\Scripts\Activate.ps1

macOS/Linux:

python3 -m venv .venv
source .venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

Environment Variables

Create a .env file in the project root:

GROQ_API_KEY=your_groq_api_key
TAVILY_API_KEY=your_tavily_api_key

The chatbot notebook loads these values with python-dotenv.

Running the Notebooks

You can run notebooks in VS Code or Jupyter Lab.

Option A: VS Code

1. Open the project in VS Code
2. Open 01-LangGraph/simple.ipynb or 02-LangGraph/chatbot.ipynb
3. Select your Python kernel
4. Run cells in order

Option B: Jupyter Lab

pip install jupyterlab
jupyter lab

Then open the notebook and execute cells sequentially.

Notebook Breakdown

01-LangGraph/simple.ipynb

• Defines a State schema with graph data
• Creates nodes like start_play, cricket, and badminton
• Uses conditional edge routing via a random selector
• Compiles and visualizes the graph
• Invokes the graph with initial state

02-LangGraph/chatbot.ipynb

• Configures external tools:
  • Arxiv query tool
  • Wikipedia query tool
  • Tavily search tool
• Initializes a Groq chat model
• Binds tools to the model
• Builds LangGraph chatbot workflows:
  • Single-pass tool-calling flow
  • Looping tool-calling flow until completion
• Executes sample prompts and prints message traces

Common Issues

• Missing API keys: Ensure .env contains both GROQ_API_KEY and TAVILY_API_KEY.
• Notebook import errors: Confirm virtual environment is active and dependencies are installed.
• Kernel mismatch: Select the interpreter from your project virtual environment.

Notes

• Keep API keys private and never commit .env to Git.
• This repository is practice-oriented and notebook-first, ideal for learning LangGraph patterns quickly.

Author

Suprit Raj