How namansingh69/exam-question-generator works
Project type and purpose
• This is a full-stack web application (“Exam Question Generator”) built with Flask (Python) on the backend and plain HTML/JS/CSS on the frontend.
• Purpose: Accept course materials (PDF, text, JSON, etc.), extract topics via OCR/PDF processors, call Google Gemini AI to generate a configurable set of exam questions, and export the result as PDF/HTML/Markdown.
File structure
• Top-level files:
• app.py – main Flask application entry point and request handlers
• setup.py – environment setup script
• requirements.txt – Python dependencies
• LICENSE, README.md
• Directories:
• static/ – frontend assets (index.html, main.js, CSS)
• uploads/ – holds user-uploaded raw files
• (README mentions temp_outputs/ for generated files, though not in the snippet)
• Key patterns:
• Single-process, monolithic Flask server
• MVC-style separation: static frontend vs. Python server logic vs. data storage
• Integration points: OCR (pytesseract), PDF tools (PyPDF2, pdf2image, pdfkit), external AI API (Google Gemini)
README for additional insights
• The “Technology Stack” section confirms Flask backend, Bootstrap/JS frontend, AI and PDF/OCR integrations.
• Features list reveals the core flows: file upload → AI analysis → question generation → export.
Detail
• Every major function (uploading, OCR, AI call, formatting, exporting) is its own node.