I

interns

OriginAI transforms research papers into startup opportunities, investor reports and pitch decks using AI.

MyDocVault is a secure, offline-first AI platform designed to help users store, organize, understand, and manage government documents in a privacy-preserving environment. The application enables users to upload documents such as Aadhaar, PAN, Passport, Driving Licence, Voter ID, educational certificates, and other official records, while ensuring that all processing happens locally without relying on external servers or internet connectivity.

Powered by an intelligent document-aware assistant, MyDocVault extracts key information, summarizes documents in simple language, answers user queries based solely on locally stored documents, and provides guidance on the documents required for various government services. The system never fabricates information, clearly identifies missing details, and prioritizes user privacy by keeping all data offline.

Key Features 🔒 Offline-first and privacy-focused document management 📄 Secure storage and organization of government documents 🤖 AI-powered document understanding and summarization 🔍 Automatic extraction of important document details 📋 Government service document requirement guidance 📂 Intelligent document search and retrieval ⚠️ Identification of missing or incomplete documents 🛡️ Local processing with no external API or internet dependency 💬 Simple, conversational AI assistant for document-related queries 📊 Structured JSON extraction for document metadata

Tech Stack: React.js, Node.js, Express.js, SQLite, OCR, Local AI Models, HTML, CSS, JavaScript

Goal: To provide citizens with a secure, intelligent, and completely offline digital document vault that simplifies document management while ensuring maximum privacy and accessibility.

Local-First PDF Q&A Assistant built using PyMuPDF4LLM and Llama.cpp. Supports PDF upload, document retrieval, and question answering using a local language model.

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

A fully local Retrieval-Augmented Generation (RAG) chatbot built using Streamlit, Ollama, ChromaDB, and open-source LLMs like Qwen and Llama.

A modern, full-featured internship management platform designed to streamline the entire internship lifecycle. Built with Next.js and MongoDB, InternLink provides comprehensive tools for interns, mentors, and administrators to track progress, manage tasks, and foster collaboration, leveraging robust GitLab integration.

Mana Ruchulu is a Telugu-language recipe sharing and discovery platform built using Streamlit. It allows users to:

Create an account and log in securely

Upload recipes with text, images, videos, or audio instructions

View and interact with other users’ recipes

Participate in weekly cooking challenges

Post short-lived “stories” about their cooking experiences

Compete on a leaderboard based on points earned from contributions

The project supports both SQLite and Supabase backends, making it deployable on platforms like Hugging Face Spaces while being scalable for production use.

Its design emphasizes Telugu cultural heritage by supporting native script and traditional dish categorization.

Doc Bot – AI Doctor Assistant is an interactive chatbot that provides doctor-style suggestions based on user-described symptoms. Built with Streamlit for a responsive and user-friendly interface, it integrates with the Dify.ai API to generate natural language responses. This project was developed as part of an internship at Swecha Telangana.

⚠️ Disclaimer: Doc Bot is for educational and informational purposes only and does not provide professional medical advice.

A simple chatbot built using Hugging Face and Streamlit that answers user queries about Indian temples. The app provides cultural, historical, and architectural insights in a conversational format.

Festival Log – A Cultural Corpus Collection Engine

Festival Log is an open-source, AI-powered Streamlit application designed to document and preserve the rich festival traditions of India. Users can submit cultural information, stories, and personal experiences related to festivals in their local language. The app automatically translates each entry into Telugu using open-source AI models and displays all entries in a collective log. It is optimized for low-bandwidth areas, supports multilingual input, and contributes to building a parallel corpus for Indian language AI research.

This project is part of the Swecha Summer of AI Internship. It includes a compliance-ready open-source AI-powered application with documentation, templates, and VS Code setup.