A recommendation system for Hacker News. Get the most similar posts for a given URL

🚀 Project Social Network 🌐

AI-based YouTube summarizer with chat, notes, and chapter generation using LangChain + MERN.

This repository provides a complete solution, including a React frontend, a Python backend with advanced RAG capabilities, and a containerized infrastructure for seamless deployment.

HidayahAI is a state-of-the-art web application that leverages advanced AI and authentic Islamic sources to provide clear, referenced answers to your questions about Islam. Using a Retrieval-Augmented Generation (RAG) pipeline, HidayahAI searches the Quran and Sahih Hadith collections, returning reliable, evidence-based responses with direct links.

The frontend of shotit, with full documentation.

Developed an AI marketplace that integrates various agents, including modular, independent agents like Professional Email Writer, Document Summarizer, YouTube Summarizer, Web Crawler, Image Generator, and Blog Writer along with a Job Agent, Case Study Agent and a Deep Research Agent, which can be combined with other agents in custom workflows.

A social book review and discovery platform with real-time, personalized recommendations using FAISS and LDA. Built with Next.js, Tailwind CSS, and TypeScript.

Experimental scripts to test code indexing and LLMs performance

Final project for the master's degree in Computer Science course "Cloud Computing" at the University of Rome "La Sapienza" (A.Y. 2022-2023)

Full-stack AI app integrating webcam-based object recognition, real-time fridge inventory tracking, and personalized recipe generation using RAG and multimodal LLMs. Combines image-to-text, semantic search, and prompt engineering to deliver context-aware, user-specific recipes.

Knowledge Server

ollama私有化部署模型，用ellectron开发chat桌面端

CMMV module for LLM integration, tokenization, RAG dataset creation, and fast FAISS-based vector search for code indexing.

AI-powered career recommendation engine leveraging the ESCO knowledge graph, transformer-based embeddings, and FAISS vector search for semantic job-skill matching.

Advanced LLM with Query, SQL & CSV RAG : advanced LLM pipeline for querying SQL/CSV using LLM & RAG

MediBot is an AI-powered medical chatbot delivering context-aware health answers via an Android app with a Flask backend. It uses advanced LLMs, FAISS vector search, and LangChain to provide accurate, real-time responses based on medical documents.

A modern, full-featured chat application that leverages Google's Gemini API

Webcam item recognition (LLaMA 3.2 Vision) + RAG recipe generation (FAISS + Mistral). Next.js + Flask + Firestore.

DEVELOPMENT OF AN AI-POWERED CAREER GUIDANCE APPLICATION FOR NAMIBIAN HIGH SCHOOL GRADUATES. Built as part of a Bachelor of Science in Computer Science research project at the University of Namibia (UNAM)