Rafia rafia
Full-Stack + ML Engineer | Building AI-powered products end-
New to Contra
Rafia is building their profile!
RAG-Based PDF Question Generator
Developed an AI-powered RAG (Retrieval-Augmented Generation) application that automatically generates questions from uploaded PDF documents. Users can upload any PDF, select the desired number of questions, and choose a difficulty level (Easy, Medium, or Hard). The system retrieves relevant information from the document and generates context-aware questions based only on the uploaded content, minimizing hallucinations and improving accuracy.
Key Features:
PDF upload and document processing
Retrieval-Augmented Generation (RAG) pipeline
Custom question count selection
Difficulty levels: Easy, Medium, Hard
Context-aware AI-generated questions
Fast, accurate, and document-grounded results
Tech Stack: Python, LangChain, Vector Database (FAISS/ChromaDB), LLM, PDF Processing, Embeddings
#AI #RAG #GenerativeAI #MachineLearning #Python #LangChain #LLM #PDF #NLP #OpenSource
1
59
An AI system that detects emotions from voice in real time, using Wav2Vec2 and a custom PyTorch classifier. Useful for applications like call centers, where understanding customer sentiment from speech alone can help teams respond better and flag issues early
1
53
Personae is a full-stack AI personal styling platform designed to solve a problem most styling apps get wrong generic recommendations that ignore your actual physical features. Built with Django REST Framework, PostgreSQL, and React, Personae uses four custom-trained computer vision models to analyze body shape, face shape, skin tone, and undertone directly from a photo or live camera capture. Based on this analysis, it generates personalized recommendations for clothing, jewelry, and makeup using a 12-season color analysis system and a fuzzy logic recommendation engine. It also includes an AI stylist chatbot powered by Gemini API for conversational styling advice. The goal is to bring the kind of personalized styling insight you'd get from a professional stylist into an accessible, AI-driven platform
Feel free to message me for a live demo.
1
83
Palette AI is an AI-powered color palette generator I built to solve a common problem for designers and developers spending too much time manually picking colors that work well together. Using Next.js and Google Gemini API, the app lets users upload a reference image or describe a mood, then instantly generates a professional color palette. Users can edit colors in real time, export them as ready-to-use Tailwind CSS variables, and save palettes for later use. It's designed to speed up the design-to-development handoff, so teams spend less time on color decisions and more time building
1
84