This project demonstrates a multi-agent chatbot system built using LangGraph, LangChain, and Azure OpenAI GPT-4o. It enables intelligent routing of user queries to specialized agents that can handle:
- 📦 Product Q&A (e.g., laptop features, specifications)
- 📑 Order Management (e.g., order status, updates)
- 💬 Small Talk (greetings, goodbyes)
The chatbot is designed to operate inside Google Colab, using userdata
for secure credential handling and modular notebooks for agent logic.
- ✅ Agent Routing with LangGraph
- 🤖 GPT-4o via Azure OpenAI API
- 🛍️ Product Q&A Agent
- 📦 Order Management Agent
- 🗨️ Small Talk Handler
- 🧠 Memory Management via
thread_id
- 📈 Visualize Agent Flow using Mermaid.js
├── product_qna_agentic_chatbot.ipynb # Defines Product QnA agent
├── orders_chatbot_custom_agent_langgraph.ipynb # Defines Order management agent
├── multi_agent_system_langgraph.ipynb # Main router agent and orchestrator
├── README.md # You are here
git clone https://github.com/shaadclt/Multi-Agent-System-LangGraph.git
cd Multi-Agent-System-LangGraph
import os
from google.colab import userdata
os.environ["AZURE_OPENAI_API_KEY"] = userdata.get('AZURE_OPENAI_API_KEY')
os.environ["AZURE_OPENAI_ENDPOINT"] = userdata.get('AZURE_OPENAI_ENDPOINT')
USER : How are you doing?
AGENT : Hello! I’m here to assist you with laptop features or order updates.
USER : Please show me the details of the order ORD-7311
AGENT : Your order ORD-7311 is currently being processed and will ship soon.
USER : Tell me about the features of SpectraBook laptop
AGENT : SpectraBook features include a 13” OLED display, 16GB RAM, and a 512GB SSD.
-
LangGraph
-
LangChain
-
Azure OpenAI
-
Python 3.10+
-
Google Colab
This project is licensed under the MIT License - see the LICENSE file for details.
Thanks to:
-
LangChain & LangGraph Teams
-
Microsoft Azure OpenAI
-
OpenAI GPT-4o for powering intelligent conversations