Noteesta: A Study Pal I Built for My Two Little Sisters
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend . What I Built My two little sisters are studying for their Bachelor of Science degrees. Preparing for exams means juggling YouTube videos, handwritten notes, and references from their teachers. Before they can even start revising, they have to bring all those materials together. I wanted to make that part easier for…
This submission is for the Hacktoberfest Weekend Challenge: Build for a Friend. The creator built Noteesta, a study pal that organizes different learning materials into a "Study Pill" with optional revision tools. The app accepts various input formats, including PDFs, Word documents, presentations, images, recorded lectures, and YouTube links.
Students can then create flashcards, multiple-choice questions, true/false questions, and a personalized study roadmap alongside their notes. Noteesta allows users to customize their study experience to fit their exam date, available study hours, preferred level of detail, and learning level.
The app consists of a Next.js frontend and a FastAPI backend, with Celery workers handling longer processing jobs. The frontend polls for progress so students can see which stage their study pill has reached. Open-weight models and open-source tools, like Docling, LangChain, faster-whisper, yt-dlp, Qwen3-VL-8B-Instruct, and nomic-embed-text, power the AI workflow.
MongoDB Atlas Vector Search, accessed through LangChain, retrieves relevant chunks for chat. SeaweedFS provides S3-compatible storage for original files and generated artifacts. The system includes a "Got a doubt?" chat for questions about the selected pill, with answers derived from retrieved source material. Notes carry source references and can include supporting visuals.
The creator tested Noteesta using their sisters' study materials, receiving positive feedback. The app is not entirely offline or entirely local but uses open models and frameworks to allow for customization and improvement as the user's needs evolve.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
