Helping Businesses AI Dreams Come To Life

Final Year Project: Building a video summarization system using Hugging Face models and implementing a recommender system using Transformer-based architecture for personalized learning experiences.

This project is an enterprise-ready Chrome extension that delivers context-aware chat powered by a RAG (retrieval-augmented generation) pipeline and Google Gemini. When a user loads any webpage and clicks 'Start Chat,' the extension extracts the page content, splits it into chunks, and converts those chunks into embeddings. The embeddings are stored and queried from a vector store; LangChain then orchestrates retrieval of the most relevant context and forwards it to Gemini, which generates the chat reply that is returned to the extension. The system supports inline rendering of math and code, delivers context-aware answers across any topic with fast, local-like interaction, and is built on a FastAPI backend with Redis Stack for sessions and vector storage—designed for secure, scalable deployments and straightforward integration.

Built a Few-Shot Consultancy Chatbot using LangChain, FastAPI, and Google Gemini for AI-driven admission guidance and document support. It solves fragmented consultancy through context-aware, multi-mode interactions and serves as a foundation for scalable multi-domain assistants.

Comprehensive machine learning pipeline for predicting real estate prices in Pakistan using Zameen.com dataset. Implemented advanced regression techniques and feature engineering.