LLM-powered financial analyst using LoRA-tuned Llama-3 and RAG pipeline to answer complex queries over SEC 10-K filings with contextual accuracy.

Flask application for Diversified Investment Portfolio Builder based on User Defined Risk Factors

Nous: A privacy-focused personal knowledge assistant using local LLMs to securely interact with your documents and enhance information retrieval.

ParmaQA.ai is an advanced QA system that combines a Retrieval-Augmented Generation (RAG) pipeline with LangChain, FAISS, and FastAPI to deliver accurate answers. It features an efficient backend for processing queries and a user-friendly frontend for seamless interaction.

Modular RAG pipeline using LangChain + FAISS + Groq Llama3 — context-aware document Q&A with clean 7-module Python architecture

Meowtron is a lightweight offline AI system with a sarcastic, cat-like personality. It detects emotions, retrieves memories, and generates personality-based responses using multiple small models.

Among the Top 8 Projects in the CreatiVerse Rocketium Gen AI AWS Hackathon 2024

DrillSense — AI-powered visual intelligence system for drilling operations. Combines SFT & RAG to summarize drilling reports, answer domain-specific queries, and generate anomaly alerts.Built with React + Tailwind and FastAPI, deployed across Vercel and GCP with a Vertex AI–trained model for real-time insights.

An AI-powered medical consultation system that provides evidence-based medication guidance using Retrieval-Augmented Generation (RAG) with comprehensive medical literature and drug interaction analysis.

A Lightweight Video RAG Framework for Multimodal Reasoning

An intelligent chatbot that allows users to upload text-based Ayurveda PDFs and ask questions based on the content using RAG (Retrieval-Augmented Generation) combining semantic search and LLM-based responses.

Production-ready NLP & RAG platform for document understanding, semantic search, and grounded question answering.

🤖 TechnoBuddy - AI-powered multilingual campus assistant chatbot for Techno International Newtown. Built with RAG architecture using LangChain, Google Gemini, and FAISS vector store. Provides instant answers about academics, placements, facilities, and campus life via Telegram. Created by HACKWARRIORS for HackTINT 2025.

CodeArchitect AI – Multi-Agent Codebase Intelligence System

A 100% offline, air-gapped Enterprise RAG assistant. Chat securely with your private document library using local Ollama models and FAISS vector search.

Youtube transript QnA chatbot by using langchain fiass RAG that user asks the question about anything in the video and the llm gives the answer according to that.

A modern Retrieval-Augmented Generation (RAG) application with a cleanly separated FastAPI backend and Streamlit frontend, powered by LangGraph for workflow orchestration. It enables PDF upload, semantic search with FAISS embeddings, and context-aware chat using Ollama (Llama2 + nomic-embed-text). Open-source offline LLM integration and deployment

A Python-based medical chatbot using Retrieval-Augmented Generation (RAG) for accurate, evidence-based responses from trusted sources.

Campus Assistance chatbot