https://github.com/shaadclt/multi-agent-system-langgraph
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 .
https://github.com/shaadclt/multi-agent-system-langgraph
azure-openai langgraph
Last synced: 3 months ago
JSON representation
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 .
- Host: GitHub
- URL: https://github.com/shaadclt/multi-agent-system-langgraph
- Owner: shaadclt
- License: mit
- Created: 2025-04-29T18:06:34.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-04-29T18:43:09.000Z (5 months ago)
- Last Synced: 2025-04-29T19:34:31.828Z (5 months ago)
- Topics: azure-openai, langgraph
- Language: Jupyter Notebook
- Homepage:
- Size: 81.1 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# š¬ LangGraph Multi-Agent Chatbot with Azure OpenAI (GPT-4o)
This project demonstrates a **multi-agent chatbot system** built using [LangGraph](https://docs.langchain.com/langgraph/), [LangChain](https://www.langchain.com/), and [Azure OpenAI GPT-4o](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/overview). It enables intelligent routing of user queries to specialized agents that can handle:
- š¦ Product Q&A (e.g., laptop features, specifications)
- š Order Management (e.g., order status, updates)
- š¬ 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.
---
## š Features
- ā
**Agent Routing with LangGraph**
- š¤ **GPT-4o via Azure OpenAI API**
- šļø Product Q&A Agent
- š¦ Order Management Agent
- šØļø Small Talk Handler
- š§ Memory Management via `thread_id`
- š Visualize Agent Flow using Mermaid.js
---
## š Project Structure
```text
āāā product_qna_agentic_chatbot.ipynb # Defines Product QnA agent
āāā orders_chatbot_custom_agent_langgraph.ipynb # Defines Order management agent
āāā multi_agent_system_langgraph.ipynb # Main router agent and orchestrator
āāā README.md # You are here
```
## š§ Setup Instructions
### 1. Clone the Repository
```bash
git clone https://github.com/shaadclt/Multi-Agent-System-LangGraph.git
cd Multi-Agent-System-LangGraph
```
### 2. Open `multi_agent_system_langgraph.ipynb` in Google Colab
### 3. Add Azure Credentials to Colab userdata
```python
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')
```
### 4. Run the Notebook Cells
## š§ Conversation Flow Example
```text
USER : How are you doing?
AGENT : Hello! Iām 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 13ā OLED display, 16GB RAM, and a 512GB SSD.
```
## š§± Built With
- LangGraph
- LangChain
- Azure OpenAI
- Python 3.10+
- Google Colab
## š License
This project is licensed under the MIT License - see the [LICENSE](LICENSE.txt) file for details.
## āØ Acknowledgements
Thanks to:
- LangChain & LangGraph Teams
- Microsoft Azure OpenAI
- OpenAI GPT-4o for powering intelligent conversations