You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A production-ready, embeddable AI chatbot widget built with Cloudflare Workers that can be integrated into any website with a single script tag. Features real-time streaming responses, RAG-powered FAQ answers, session persistence, and dark/light mode support.
An enterprise-grade, full-stack AI travel planner which provides data-driven itineraries for Lucknow, India and showcases production-ready architecture, combining a FastAPI backend with a Streamlit frontend. It leverages an advanced agentic RAG system, context-aware responses by integrating a local knowledge base with live, external APIs.
PerfectPick is an AI-powered smartphone recommendation system built with Flask and Postgres for session management, AstraDB for vector storage, and hybrid retrieval using BM25 and BGE embeddings. Deployed on GCP with Docker and Kubernetes, integrated with Prometheus and Grafana for scalable, production-grade performance and MLOps observability.
A conversational chatbot that remembers context and retrieves external information using Retrieval-Augmented Generation (RAG) with LangChain, ChromaDB, local BGE embeddings, and Google Gemini 2.5 Flash.
A Python-based tool that suggests movies by analyzing user preferences and real-time streaming availability. It helps users skip the 'endless scroll' and find exactly where to watch their next favorite movie across different subscription/free platforms.
A Retrieval-Augmented Generation (RAG) application built with Streamlit that enables users to upload PDF documents and engage in a grounded conversation with the content. This project implements a full processing pipeline including text extraction, chunking, and vector embeddings to provide accurate Q&A with verifiable citations.
Mini project for NLP: FineTuned a BGE encoder using domain specific data and then paired it with a finetuned BERT uncased model for QnA retrieval for getting top3 relevant answers.
High-precision Content Retrieval Engine with automated model comparison and evaluation. Implements semantic boundary-aware chunking and RRF-based hybrid search for optimized document retrieval.