StudyEase AI 如何用 Gemma 3 簡化温習

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

What I Built

As a CSE student, I know that preparing for exams often means going through long lecture notes and manually organizing important information.

To make this process easier, I built StudyEase AI, a simple AI-powered study assistant that turns study notes into useful revision materials.

StudyEase AI offers three features:

• Short Summary: Condenses lengthy notes into shorter explanations.
• Key Revision Points: Organizes important information for quick revision.
• Practice Questions: Generates questions from the provided notes to support self-assessment.

The goal is simple: spend less time organizing notes and more time understanding what you're studying.

Demo

🎥 Watch the demo: https://youtu.be/iBl5yhgl6xI

The video demonstrates the application and its three main features.

Code

💻 GitHub Repository: https://github.com/Rehu33/studyease-ai

The repository contains the source code, setup instructions, dependencies, and application screenshots.

How I Built It

I built StudyEase AI using Python and Streamlit, with Ollama running the Gemma 3 1B model locally.

The main technologies are:

• Python for the application logic.
• Streamlit for the user interface.
• Ollama for running the language model locally.
• Gemma 3 1B for generating study materials.
• Requests for communicating with the local Ollama API.

The application takes the user's notes, combines them with instructions for the selected task, and sends the prompt to the locally running model. The generated response is then displayed in the interface.

I also included instructions in the prompt to use the supplied notes, avoid inventing unsupported facts, and acknowledge missing information.

Why Does Open Innovation Matter?

For a learning project like StudyEase AI, open-weight models make experimentation more accessible.

Using Gemma 3 1B through Ollama allowed me to run inference on my own computer instead of depending on a paid, cloud-hosted AI API for every request.

This approach gives users more control over their workflow and can help keep their study notes on their own machine during local inference. After the model has been downloaded, text generation can work without sending prompts to a remote AI service, provided the local setup is running correctly.

It also gave me an opportunity to learn how an AI model can be integrated into a practical application using accessible tools.

I believe open innovation matters because students and independent developers should be able to experiment, build useful tools, and learn without needing an expensive AI infrastructure.

The Lazy Payoff

Instead of manually rewriting notes into summaries, revision points, and practice questions, students can generate an initial set of study materials from a single set of notes.

StudyEase AI is a small first version, but it demonstrates how local AI can reduce repetitive study preparation and make revision workflows easier.

AI-generated content should still be checked against the original notes, especially before an exam.

Prize Categories

• Best Use of Gemma

StudyEase AI uses the Gemma 3 1B model through Ollama as its core text-generation engine.

Built with curiosity as a CSE student, and with plenty more to learn. 📚