Key learning

  • This was highly programming intensive course where I learned to build the enterprise level web applications using various technologies like Java, Servlet, React, PostgreSQL, MongoDB, ElasticSearch etc..
  • At the end I had two nice projects which gave great experience to collaborate on building a project as well as web development and AI development skills

Projects

Project 1: SmartHome Website

Phase-1: Basic Website with UI

  • A servlet based web application that allows customers to place orders online from smartHome Website
  • Role based access control for StoreManager, Retailer and Customer
  • presented complex product details on product catalog page
  • Initially started with Hashmap to store the data in XML file
  • Used JSP for the front end and Servlet for the backend

Phase-2: Database Integration

  • using object-oriented design principles and utilized the MVC architecture to create web-based enterprise application
  • Created the database schema and integrated with the application
  • Used PostgreSQL for Customer, order and product data
  • Used MongoDB for storing the product reviews and ratings

Phase-3: Added Analytics report

  • Added analytics on the top of the existing website, where added the functionality of Inventory Report and Sales Report using Google charts.

Phase-4: AI based customer service chatbot

  • Using OpenAI model gpt-4o-mini, added the functionality of Customer Service where user can upload the image of damaged package in chatbot and get the response of status of package with further instructions.
  • Added GenAI based functionality to recommend a product and search the reviews.
  • Used OpenAI model text-embedding-3-small for generating the embeddings and user ElasticSearch to store the embeddings.
  • Drawback: After doing these 5 assignments for single projects, It is incomplete to integrate all into the single fully funtional project. But I have learned a lot from this project and I am looking forward to integrate all these features into single project.

Project 2 - ClothAI: Multi-agent and Multimadal AI Chatbot using Autogen

  • code:

Phase-1: Recommendation Agent

  • Capable of recommending the products based of the users preferences in natural language. It also allows the purchasing of the recommended product if the user wants to buy it and also update in the database with prompt confirmation of order. A user can also see the status of the order based of the orderid
  • Used the GroupChat class in Autogen to effectively orchestrate the conversation between multiple agents by keeping the Human in the loop
  • created Backend APIs using Flask and React for the front end

Demo-1: https://youtu.be/5gD1kuKxsYE

Phase-2: Fraud Detection Agent and Shipping Status Agent

  • Fraud Detection Agent is capable of detecting the fraud based on the OCR image of bill uploaded by the customer. We used gpt-4o-mini for all of the tasks performed by the agents. We also have our agent promptly reply with the status of the fraud by analyzing the image and double checking with values in database
  • Shipping Status Agent is capable of providing the status of the damaged package and defective product by analyzing the image using VisionCapability class in Autogen

Demo: 2: https://youtu.be/kMJhXsEgpmg