vectore-database

Multi-agent enterprise AI knowledge platform with Agentic RAG, ACL-aware retrieval, and hybrid intelligence, built with LangGraph, FastAPI, Next.js, PostgreSQL, pgvector, and BGE.

🕸️ Self-Optimizing Multi-Agent AI System on AWS — Routes tasks to specialized AI agents (Coder, Researcher, Summarizer) with auto-verification, self-correction, and vector-cached memory. Built with Step Functions, Bedrock, and OpenSearch Serverless.

A professional-grade Retrieval-Augmented Generation (RAG) platform that transforms your documents into an interactive knowledge base. Built for high-performance semantic search and context-aware conversations.

C2C e-commerce marketplace prototype app for users to trade goods and services

MediBot is an AI-powered medical chatbot that leverages state-of-the-art language models and vector search to answer user queries based on a curated set of medical PDF documents. It uses Streamlit for the user interface, LangChain for LLM orchestration, and FAISS for efficient vector search.

A curated list of my AI/ML projects — FYP, computer vision, NLP, and more.

GenAI | RAG-based multilingual farming chatbot with voice I/O using ChromaDB, LangChain, LLaMA 3.3 (Groq), and Web Speech API

Built an AI-based multi-document chatbot using Retrieval-Augmented Generation (RAG) that enables conversational querying of PDFs with semantic search.

Production RAG patterns and semantic drift detection for Microsoft Fabric

AI-powered PDF question-answering system using Experimental Retrieval-Augmented Generation project using local embeddings, FAISS indexing, and Mistral via Ollama.

Gen AI implementation for student's support to prepare for specific module

Retrieval-Augmented Generation (RAG) application for answering questions from PDF documents using LangChain, FAISS, and Google Gemini.

Chat with PDF - simple setup for creating and testing RAG and LLM capabilities

🎥 YouTube RAG Q&A App - Learn LangChain through Practice

Groq-powered Retrieval-Augmented Generation (RAG) system with semantic search, source citation, and Streamlit UI.

Chat with your PDFs — a RAG app that embeds documents into a vector store and answers questions with source-grounded context.

⚡ Production-style RAG Chat API — FastAPI + Groq + ChromaDB + Postgres with multi-turn conversations, server-side history, and grounded Q&A

Web app for PDF document ingestion with interactive preview, content editing, and vector database storage. Used for testing the similarity search

🎥 Ask questions about YouTube videos using AI with this RAG app, which leverages transcripts and embeddings for context-aware answers.