A SIH-2023 project featuring an offline LLM for document summarization and Q&A, with Node.js APIs and OCR for text-based interactions.

A full-stack application that allows users to analyze and chat about code repositories using Google's Generative AI and LangChain. The system clones GitHub repositories, processes the code files, and enables intelligent conversations about the codebase.

Chat-with-Your-Documents is an AI-powered document chatbot using RAG, FastAPI, and React.js for local PDF question answering.

Rag Qna

For Educational Use Only (But Really) RAG-LLM workflow for building a knowledge-base around a canvas system

Atomic is a full-stack AI-powered contextual chatbot application built with React, Node.js, and Google Gemini AI. The application features multiple AI personalities, real-time chat functionality, user authentication, and persistent memory using vector embeddings.

VLib is a digital library platform targeting college library systems that utilises a vector database for discovering required resources and thereby making information accessible to all users irrespective of their knowledge level. It overcomes the incapability of present systems to handle descriptive queries thereby limiting information access.

A RAG with node.js, neo4j vector db, ollama, langchain and openai

This repository contains the implementation of a media search application using Google Cloud Spanner and Vertex AI for generating and searching embeddings.

Pinecone To Store Vector Embedding And Embedded Search

Backend for a RAG-powered news chatbot providing real-time AI responses, semantic search, and news retrieval using Node.js, Socket.IO, PostgreSQL, Redis, and Qdrant.

Mind Vault is an AI-driven knowledge transfer system that extracts, organizes, and summarizes enterprise documents into a searchable knowledge base. It prevents knowledge loss, accelerates onboarding, and enhances productivity by delivering semantic search, automated insights, and traceable information access across teams.

📄 Create a lightweight Node.js backend for Retrieval-Augmented Generation, enabling efficient document embedding, storage, and semantic search.

This repository contains my practice and experiments with vector search and semantic searching using various vector databases.

GenAI Search Assistant is a modern web app that combines Google Search and Gemini AI to deliver context-aware answers. It uses RAG (Retrieval-Augmented Generation) to fetch, analyze, and summarize information from multiple sources. Features include voice search, interactive suggestions, AI-generated summaries, and a sleek glassmorphism UI.

Use case of similarity recommendations for food products with vector database

User uploads a selfie and the application will use Vector search to decide which Starwars character you look the most like, Powered by MongoDB Atlas Vector Search and Python Face Recognition API. Frontend: React

AI-powered medical clinic chatbot using Model Context Protocol (MCP) with Google Gemini AI. Features appointment management, clinic information retrieval via ChromaDB vector search, and a responsive React frontend. Built with Node.js, MongoDB, and MCP Server architecture.