🤖 Basic Chatbot using LangGraph & Groq API

Welcome to this minimal yet functional chatbot project that leverages the LangGraph Graph API and Groq's LLaMA3-8B-8192 model! This chatbot demonstrates how to structure conversational flows using a graph-based state machine and large language models.

---

📌 Features

• 🌐 Built using LangGraph – A graph-based framework for building LLM-powered applications.
• 🚀 Powered by Groq API with LLaMA3-8B-8192 model.
• 🔁 Graph execution flow: Define states → Add LLM node → Connect via edges → Compile → Invoke.
• 🧠 Stateful memory with message history via add_messages.
• 🔎 Visualizes graph using Mermaid.

---

📁 Project Structure

.
├── 1-basicchatbot.ipynb     # Jupyter Notebook with complete chatbot code
├── .env                     # Stores your Groq API Key
└── README.md                # Project documentation

---

🧰 Requirements

Make sure you have the following Python packages installed:

pip install langgraph langchain langchain-groq python-dotenv

---

🔐 .env Configuration

Create a .env file in the same directory as your notebook/script and add:

GROQ_API_KEY=your_groq_api_key_here

---

🧱 How It Works

1. Define State

class State(TypedDict):
    messages: Annotated[list, add_messages]

The chatbot keeps track of all messages in a list using add_messages, which appends new user/LLM messages to the state.

---

2. Initialize Groq LLM

from langchain_groq import ChatGroq
llm = ChatGroq(model="llama3-8b-8192")

You can also use init_chat_model("groq:llama3-8b-8192") for compatibility with LangChain.

---

3. Define Node Function

def chatbot(state: State):
    return {"messages": [llm.invoke(state["messages"])]}

The chatbot node takes the current state and returns a new message generated by the LLM.

---

4. Build and Compile Graph

graph_builder.add_node("llmchatbot", chatbot)
graph_builder.add_edge(START, "llmchatbot")
graph_builder.add_edge("llmchatbot", END)

graph = graph_builder.compile()

This builds the LangGraph with a simple START → LLM → END flow.

---

5. Invoke the Chatbot

response = graph.invoke({"messages": "Hiiii"})
print(response["messages"][-1].content)

---

🧠 Graph Visualization

To visualize the LangGraph structure:

from IPython.display import Image, display
display(Image(graph.get_graph().draw_mermaid_png()))

---

📸 Demo Output

Input:  Hiiii
Output: Hello! How can I help you today?

---

💡 Notes

• This is a minimal working prototype. You can extend it with more nodes like context handling, retrieval, tools, or memory chains.
• You can swap out Groq with OpenAI, Mistral, or any other LLM backend supported by LangChain.
• Don't forget to keep your API keys secure.

---

✨ Credits

• 🧠 LangGraph
• ⚡ Groq API
• 🤖 LangChain

---

📜 License

This project is licensed under the MIT License. Feel free to modify and build upon it!

---

🧑‍💻 Author

Jiya Shetty 📧 jiyashetty173@somaiya.edu 👩‍🎓 TY BTech Electronics and Computer Engineering 📍 K. J. Somaiya College of Engineering