About My Projects

Explore my projects that showcase my skills in software development and problem-solving.

VS Code AI Chat Assistant

TypeScript | React | OpenRouter API | Hugging Face BLIP | Markdown Previews

GitHub 🎥 Demo Video Project Overview

Plant Disease Detection

Python | Flask | PyTorch | CNN | Deep Learning | SQLite | Frontend

GitHub 🎥 Demo Video Project Overview

AI Sudoku Solver

Python | Neural Net | CSP | SQLite | Flask | UI

GitHub 🎥 Demo Video Project Overview

Portfolio Website

HTML | CSS | JS | Responsive Design

GitHub 🎥 Demo Video Project Overview

Project 1: VS Code AI Chat Assistant

A smart, React-powered AI chat assistant built directly into Visual Studio Code. It understands code context, supports inline file mentions like @filename, and generates or modifies code using natural language prompts. Built using TypeScript, React WebView, and integrates real AI APIs (OpenRouter, Hugging Face BLIP) or mock fallback for demos.

Contextual Chat Panel

Integrated WebView React UI inside VS Code with full markdown and code block rendering.

@File Mentions

Reference workspace files using @filename to auto-fetch and embed contents in chat.

Image Captioning

Generates captions for uploaded images using Hugging Face BLIP model – supports .jpg/.png.

AI Integration

Supports OpenRouter (free) and OpenAI (paid) for natural language code generation and help.

Open Source

Fully open source on GitHub. Easily extendable with your own features and models.

VS Code AI Chat Assistant View.

VS Code ai assistant

Writing Code Using OpenRouter.

VS Code ai assistant VS Code ai assistant Image Upload

Supports image upload using @filename.

VS Code ai assistant Image Upload

Project Demonstration

Watch how the AI Assistant interacts with workspace files and generates responses in real-time.

Project 2: Plant Disease Detection

This project uses convolutional neural networks to classify plant diseases across 14 crop types and 39 different disease classes with remarkable accuracy. It serves farmers and agricultural researchers for early disease detection using image-based diagnosis.

14 Crops, 39 Classes

Supports Tomato, Apple, Corn, Potato, Grape, and more. Distinguishes both healthy and diseased states.

Trained Deep Models

Uses CNN, ResNet18, MobileNetV2, and EfficientNetB0 architectures. Models trained on 54K images using PyTorch.

99% Accuracy

Tested and validated with early stopping, checkpointing, and visualization of training vs. validation performance.

Flask Web App

Complete user interface with multi-model selection, history tracking, real-time predictions, and supplement advice.

CSV Integration

Displays predicted class, disease description, prevention steps, and supplement information fetched from CSVs.

Real Image Support

Works with camera or gallery images. Robust predictions after training on real-world leaf image dataset.

Screenshots

User uploads a leaf image .

Web App Prediction UI

Selects model.

Web App Prediction UI

Receives disease name, description, and prevention steps.

Web App Prediction UI

Confusion matrix comparison of CNN. Validated with 97% accuracy.

Confusion Matrix

Confusion matrix comparison of ResNet18. Validated with 99.4% accuracy.

Confusion Matrix

Confusion matrix comparison of MobileNetV2. Validated with 99.5% accuracy.

Confusion Matrix

Confusion matrix comparison of EfficientNetB0. Validated with 99.6% accuracy.

Confusion Matrix

Project Demonstration

Watch the video to see how the Plant Disease Detection system works in real-time.

<

Project 3: AI Sudoku Solver & Generator

A full-stack AI-powered Sudoku Web App that allows users to generate, solve, and validate puzzles of varying grid sizes (4x4, 9x9, 16x16). The app features both a Constraint Satisfaction Problem (CSP) solver for all grid sizes and a Neural Network solver specifically for 9x9 puzzles. Players can track their scores, upload avatars, and view a global leaderboard. Built using Flask (backend), HTML/CSS/JS (frontend), and SQLite (for storing scores).

Interactive interface of the AI Sudoku web app with generation, solving, and leaderboard features.

AI Sudoku Solver Screenshot

Multi-size Support

Play and solve 4x4, 9x9, or 16x16 Sudoku puzzles with adjustable difficulty.

AI Solvers

Backed by CSP for logical solving and a neural network model trained specifically for 9x9 puzzles.

Real-time Validation

Validate puzzle progress live and get immediate feedback on correctness.

Leaderboard

Track and display top scores with time, difficulty, and optional avatars.

Avatar Upload

Upload custom avatars to personalize your leaderboard appearance.

SQLite Integration

Store player performance securely using SQLAlchemy and SQLite.

Project Demonstration

Watch how the AI Sudoku Solver works with CSP and Neural Network methods in real-time.

Project 4: Personal Portfolio Website

A responsive and elegant multi-page portfolio crafted using HTML, CSS, and JavaScript. This website reflects my design philosophy—clean, user-centric, and approachable. It showcases my technical projects, resume, experience, and contact information while ensuring mobile-first responsiveness and light/dark theming.

Elegant UI

Soft colors, rounded sections, and gentle animations give the site a welcoming feel.

Clean Codebase

Structured HTML, modular CSS, and reusable design patterns ensure maintainability.

Fully Responsive

Optimized for desktops, tablets, and mobile devices with fluid layouts.

Dark Mode Toggle

Built-in toggle to switch between light and dark themes for user preference.

Resume Download

One-click access to my resume via a well-placed CTA on the resume page.

Personal Touch

Branded with my name, personality, and visuals to reflect who I am as a developer.

Screenshot of my personal portfolio website—designed for clarity and engagement.

Portfolio Website Screenshot

Project Demonstration

A short walkthrough of my personal portfolio site, layout, and responsive features.