S

swecha

https://hackathon-qd3o.vercel.app/

Scan any invoice or bill image — AI extracts the data, builds your financial dashboard. Fully offline. CPU only.

Interview Simulator

A real-time AI interview coach built with a Bun backend and Groq AI integration. This project includes:

browser-based job description and persona setup resume upload and text extraction for PDFs/DOCX/TXT live streamed interview assistant replies via SSE transcript export and review features frontend mic support and keyboard shortcuts

Use this file as the folder-level description for the project.

Offline-first lecture transcription and structured study data extraction CLI/PWA.

offline-first, AI-powered FIR draft assistant. Uses local LLMs (Ollama) and on-device OCR to ecurely extract structured data from sensitive complaint documents without the cloud.

Offline Investigation Intelligence Platform

WaterWatch is an app designed to address the water related issues in Telangana like pipe leaks, water shortages, other complaints.

AquaAlert — A civic water supply complaint management system for Hyderabad. Citizens can report issues, track complaints, and officers can manage resolutions via an admin dashboard.

Smart Food Finder is a preference-based restaurant recommendation platform that helps users discover nearby dining options using their location, budget, cuisine preferences, and dining style.

Lightweight local RAG document chatbot with multilingual support (en/hi/te).

NyayaSetu is an AI-powered Citizen Rights and Civic Governance Assistant that helps users understand laws, civic services, RTI procedures, and government schemes using Retrieval-Augmented Generation.

WaterWatch is a water quality complaint reporting platform built for the Swecha hackathon

The Image Captioning project is an AI-based system that automatically generates textual descriptions for images. It combines computer vision and natural language processing (NLP) techniques to understand the content of an image and produce a human-readable caption.

The system uses deep learning models, typically a Convolutional Neural Network (CNN) for extracting image features and a Recurrent Neural Network (RNN) or Transformer-based model for generating sentences. This enables applications such as assisting visually impaired users, enhancing image search engines, and automating social media content tagging.

This is the Bilingual AI powered chatbot that I developed as a part of the Summer of AI internship task.

AI-powered chatbot application with React frontend and Node.js backend for interactive conversations

Project Title: Local Proverbs & Folk Wisdom Collector Description: A multilingual, AI-powered Streamlit app that collects local proverbs, sayings, and cultural wisdom from Indian communities. Built as part of the Summer of AI 2025 initiative to preserve linguistic and cultural diversity.

A crowdsourced platform to collect and categorize cultural data from across India for the Swecha Corpus project.

🌟 VakyaVibe.ai – Indian Language Corpus Collection Platform VakyaVibe.ai is an open-source, community-powered web application designed to preserve and celebrate India's rich linguistic and cultural heritage. It serves as a multilingual Corpus Collection Engine, enabling users to contribute and explore proverbs, slang words, and tongue twisters across 10+ Indian languages and dialects.

🚀 Features 🌐 Multilingual Support – Hindi, Telugu, Tamil, Bengali, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, and more

🤖 AI-Powered Intelligence – Mistral AI (primary), OpenAI (fallback), Ollama (local)

🗳️ Community Contributions – Submit, vote, and categorize cultural expressions

📊 Admin Dashboard – User stats, language analytics, CSV/JSON export

🤗 Hugging Face Integration – Dataset sync, backup, and model-ready formats

📱 Modern UX – Mobile-friendly, offline-first, PWA, dark/light modes

🔐 Data Governance – Validation, version control, and privacy safeguards

🕉️ Mandir__Mithra – AI-Powered Temple Guide

A bilingual (English + Telugu) chatbot that guides users through sacred temples of Telangana & Andhra Pradesh.

Features:

🏛️ 20+ temples with history, architecture, images 💬 Interactive chatbot interface 🌍 AI-powered: Fetches real-time facts from Wikipedia 🔊 Text-to-Speech in Telugu & English 🚀 Static web app deployed on Hugging Face

Built as part of SOAI 2025 internship.

This project showcases two chatbot implementations: one using Hugging Face Transformers for building a general-purpose conversational AI, and another Indic-language chatbot powered by Dify.AI with Gemini integration for multilingual support. The first focuses on simplicity and flexibility with open-source models, while the second enables natural conversations in Indian languages using a no-code orchestration platform.