📚 Automate knowledge transfer with Mind Vault, an AI-driven system that converts unstructured data into searchable insights, enhancing onboarding and team efficiency.

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

Personal AI Assistant with RAG (Retrieval-Augmented Generation) - OpenAI GPT-4 + Pinecone Vector DB + Flask. Live Demo: https://diligent-jarvis.onrender.com

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

Media broker for serving video preview for shotit

VoiceRAG combines voice interaction with retrieval-augmented generation (RAG) for intelligent, conversational access to your stored knowledge. It integrates ElevenLabs Voice Agents, OpenAI GPT models, Supabase/Vector databases, and n8n automations for smooth knowledge-to-voice workflows.

The ultimate brain of Shotit, in charge of task coordination.

A website where you can upload dfferent type of content like texts, websites, youtube videos and pdf files. And after uploading can chat with all the knowledge base you have uploaded.

A mental health chatbot with intelligent memory.

Portable vector database with auto-installing Ollama embeddings. Zero-config semantic search via SQLite.

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.

Docsally is your smart PDF assistant, powered by Ollama—instantly understanding your documents and answering your questions with AI insights.

Experimental HNSW Index implementation.

PDFGenie 📄🧞‍♂️ – Ask questions from your PDFs using AI! Generate embeddings with Gemini ✨, fetch content with GROQ 📚, and search fast via Pinecone ⚡. Your PDF, your answers! 🧠💬

Convenience Docker Postgres images with pre-installed pgvector

Aura — a full-stack conversational assistant: React + Vite frontend, Express + MongoDB backend, Pinecone + Google GenAI integration.

The department of higher education under MoE like any other ministry have functional rules, regulations, policies, schemes, projects etc. The department while conducting day to day operations and dealing with institutions need to refer and analyze the data from multiple sources. For authorities and decisions makers, its critical to identify right

AI-powered health & nutrition app offering personalized care, meal plans, baby tracking, pregnancy support, and smart hospital location services.

This project implements a Retrieval-Augmented Generation (RAG) system in JavaScript. It allows you to chat with a PDF document by leveraging the power of Large Language Models (LLMs) and vector databases.