top of page

Basic Chatbot - End to End Agentic AI Chatbot

Problem Statement:

​

So far, I have been exploring LangGraph concepts like chat chains, workflows, RAGs, human-in-the-loop, and AI agents mainly inside Jupyter Notebooks. While these experiments were useful for learning, they are not enough when it comes to real-world AI development. In actual projects, we need modular coding, scalability, proper structure, and deployment to make applications production-ready.

 

The challenge for me now is to move beyond notebook-based experiments and build an end-to-end AI application that brings all these concepts together, follows industry best practices, and can be deployed on platforms like Hugging Face and FastAPI for real use cases.

Project Details:

 

 

Overview

 

In this project, I am building an end-to-end AI application using LangGraph. The key focus areas are modular coding, scalability, industry-standard practices, and deployment. This project takes the concepts we learned in earlier modules—such as chat chains, workflows, Retrieval Augmented Generation (RAGs), human-in-the-loop systems, and AI agents—and applies them in a practical, real-world environment.

 

Application to be Developed

 

  • Basic Chatbot

    • A simple yet powerful chatbot built using LLaMA 3 API.

    • Handles natural conversations and demonstrates how to set up a stateful conversational agent.

​

Technical Approach

 

  • The entire project will be built with a modular structure using Python, LangGraph, and class-based coding.

  • This modular design ensures that the code is scalable, reusable, and easy to maintain, following industry standards.

  • Core concepts like state graphs and agent workflows will be applied to ensure robustness.

 

Deployment

​

  • The first deployment will be done using Streamlit on Hugging Face Spaces, making the application accessible via a web interface.

​

Outcome

​

This project demonstrates how to move from basic Jupyter Notebook experiments to a fully functional, production-ready AI application. By the end, the project will serve as a complete reference for:

 

  • Best practices in AI application development

  • Building modular and scalable solutions

  • Deploying AI projects in real-world environments

Final Output:

​

bottom of page