StudySage — Offline & Online AI Note Assistant
AI & MLPrivacy-first AI study assistant with offline Seq2Seq summarization, OpenCV OCR pipeline & automated quiz generation.
infoProject Overview
StudySage is a privacy-first AI study companion powered by local Seq2Seq transformer models (distilbart-cnn-12-6) and cloud inference fallbacks. It processes lecture slides and screenshot captures through an adaptive OpenCV image pipeline (denoising, grayscaling, Otsu thresholding, morphological operations) paired with Tesseract OCR. It automatically generates multiple-choice quizzes (MCQs) via NLTK keyword analysis, compiles executive A4 PDF reports in Light or Obsidian Dark themes, and runs across 5 unified user interfaces.
layersTechnology Stack
auto_awesomeKey Features
9 Highlights5 Unified User Interfaces
Single core logic engine powering a single-port React SPA, Streamlit web app, CustomTkinter desktop GUI, Telegram bot daemon, and interactive CLI.
Smart Local Summarization
Runs local Seq2Seq transformer models (distilbart-cnn-12-6) for 100% offline document summarization without sending notes to remote servers.
Cloud API Fallback
Online mode uses Hugging Face Inference API for ultra-fast summarization of larger text snippets when internet connection is available.
Adaptive OpenCV Pipeline
Preprocesses screenshot captures using grayscaling, Gaussian blur denoising, Otsu thresholding, and morphological operations for maximum OCR accuracy.
Tesseract OCR Engine
Extracts clean text from lecture slides, scanned book pages, and screenshot clippings with automatic language detection.
Interactive MCQ Board
Generates multiple-choice quizzes automatically using NLTK sentence tokenization and keyword frequency analysis with interactive scoring boards.
Executive A4 PDF Exporter
Compiles structured summaries and generated quizzes into publication-ready A4 PDF reports via ReportLab in Light or Obsidian Dark themes.
Single-Port Unified Serving
Built-in FastAPI server builds and serves the static React frontend and REST API on a single unified port (8000).
Multi-Format Document Loaders
Native document loaders process raw .txt, .md, .pdf, .png, .jpg, .bmp, and .tiff files effortlessly.
photo_libraryInterface & Screenshot Gallery
React Web App — Summarization & Extraction
Clean, responsive React SPA with dark/light themes, OCR file upload, and real-time distilbart Seq2Seq summary generation.
MCQ Quiz Board & Scoring
Automated multiple-choice question generation with instant grading, explanations, and interactive scoreboards.
Streamlit Cloud Web Application
Lightweight cloud deployment on Streamlit Cloud with OCR processing, custom prompt parameters, and instant PDF downloads.
CustomTkinter Desktop GUI
Native 100% offline desktop interface built with CustomTkinter for privacy-focused local study sessions.
playlist_add_checkQuick Start & Setup Guide
$git clone https://github.com/sizwinz/StudySage-Offline-Online-AI-Note-Assistant.git && cd StudySage-Offline-Online-AI-Note-Assistant && python -m venv .venv$source .venv/bin/activate # On Windows: .venv\Scripts\activate
pip install -r requirements.txt$cd apps/web_app && npm install && npm run build && cd ../.. && python apps/api/server.pyOffline mode requires local PyTorch runtime. Online mode uses Hugging Face Inference API.