O

ollama

NyayaBloom is an AI-powered Judicial Intelligence Platform designed to democratize legal knowledge and improve judicial transparency across India. The platform enables citizens, lawyers, law students, researchers, journalists, and judicial professionals to access legal information, understand judicial processes, explore case precedents, and improve legal literacy through a multilingual AI-powered ecosystem. Instead of replacing judges, courts, or legal professionals, NyayaBloom serves as an intelligent legal knowledge assistant that simplifies legal information and promotes informed civic participation.

Smriti is an AI-powered heritage exploration platform that brings Telangana's monuments, history, culture, and tourist destinations to life through intelligent storytelling and immersive digital experiences. The platform preserves cultural heritage by combining artificial intelligence, interactive experiences, and historical insights to help users discover the stories behind every monument and place.

MedRepo is an offline, CPU-first AI application designed to convert medical Complete Blood Count (CBC) reports from PDFs or images into clean, structured JSON. The project prioritizes patient privacy by processing all data locally without requiring an internet connection or cloud services. It combines OCR and lightweight local language models to accurately extract and organize medical information for further analysis or integration with healthcare applications. Built with a modular architecture, MedRepo is easy to set up, extend, and maintain. The project aims to make medical report digitization faster, more secure, and accessible on low-resource devices while supporting future enhancements and broader diagnostic report formats.

Offline-first, CPU-first receipt and invoice OCR, local Qwen categorization, structured expense reporting, and JSON/CSV export.

LectureLens is a secure, localized, multi-modal ingestion pipeline that transforms raw educational assets into structured, high-retention study matrices. Built entirely on an offline-first philosophy, the system intercepts dense lecture audio streams and multi-page technical PDFs, running them through an isolated edge-computing layer to generate interactive flashcards, core concept maps, and dynamic glossaries without leaking sensitive user data to third-party cloud vectors.

Lightweight local-first RAG chatbot built with Streamlit, Ollama, ChromaDB, SQLite, and local quality checks.

Local-First Document Q&A with RAG using Ollama — Find-Retrieve-Answer pattern

AI Document Assistant - A local-first RAG chatbot built with Streamlit, LangChain, Ollama, and ChromaDB for PDF question answering, OCR, summarization, and resume analysis.

TravelSathi is an AI-powered travel planning assistant developed for the Swecha Hackathon. It combines Retrieval-Augmented Generation (RAG), offline local language models (via Ollama), and multilingual support to generate personalized itineraries, budget estimations, local phrases, and destination recommendations.

AI Chat Assistant is a conversational platform built using Streamlit, designed to integrate multiple Large Language Models (LLMs) such as Ollama (local hosting), OpenAI, and Google Gemini. The system provides a flexible interface for seamless interaction across different models while supporting customization through fine-tuned domain-specific datasets. Its architecture emphasizes scalability, multilingual support (including Indic languages), and accessibility, making it suitable for both personal productivity and enterprise use.

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.

DietBot is a chatbot that helps users track meals, suggest diet plans, and promote healthy eating habits. It supports personalized recommendations and integrates with nutrition data sources.

🚀 VidyaVaani - Revolutionary AI-Powered Teacher's Assistant for Regional Schools

VidyaVaani is a cutting-edge, production-ready AI education platform that democratizes artificial intelligence for India's diverse linguistic landscape. Built with enterprise-grade architecture and powered by state-of-the-art open-source AI models, this platform bridges the digital divide by bringing advanced AI capabilities to government and rural schools.

🌟 Key Features: • Multilingual AI Excellence: Native support for 12+ Indic languages (Hindi, Telugu, Tamil, Kannada, Bengali, Marathi, Gujarati, Punjabi, Odia, Malayalam, Assamese) • Open Source AI Engine: Integration with Ollama, Gemma, Llama, and Mistral models for unlimited, cost-free AI processing • Smart Document Processing: AI-powered text extraction from PDFs, images, and documents • Dynamic Content Generation: Automated creation of quizzes, explanations, translations, and Q&A sessions • Voice-First Interface: Voice commands and TTS in regional languages • Production-Ready Architecture: Docker, Redis caching, Celery task queuing

Technical Stack: • Frontend: Streamlit with modern UI/UX • Backend: Flask REST API with JWT authentication • AI Integration: Local AI models via Ollama with cloud fallbacks • Database: SQLAlchemy with SQLite • DevOps: Docker Compose, production scripts, CI/CD templates

🎯 Impact & Vision: Empowers millions of teachers across India with AI co-pilots that understand their cultural and linguistic context. VidyaVaani is a revolution in educational technology that makes AI accessible, affordable, and culturally relevant for every Indian classroom.

🔬 Research & Innovation: Perfect for AI education research, multilingual model development, and educational technology innovation. Open-source architecture enables community contributions.

Built with ❤️ for India's educational excellence by the Swecha community.

This project, "Ruchi: Your Culinary Assistant," is a multilingual chatbot that provides cooking advice. Built with Streamlit in Python, it uses different Large Language Models (LLMs) for English and Telugu responses to offer culturally relevant recipes and tips.