I Built a Local AI Study Assistant for a Friend with Gemma and Ollama

Description and use

A local study assistant built with Gemma 3 1B via Ollama that turns long notes into concise summaries, questions, and answers, preserving privacy and speeding up revision.

Problem

Students spend excessive time converting long class notes into revision material, risking privacy by sending notes to external AI services.

Outcome

The MVP successfully produces concise study material locally without external API calls, preserving privacy and reducing preparation time.

Workflow

• Paste notes into the web interface
• Click "Generate Study Material"
• Flask forwards notes to local Ollama API
• Ollama runs Gemma 3 1B to generate summary, questions, answers
• Result displayed in browser for review

Evidence

I built this for a friend who spends a lot of time going through college notes before exams and creating revision material manually.

Source

The application has a very small architecture: Student → Study Notes → Flask Web App → Ollama → Gemma 3 1B → Summary + Questions + Answers → Student

Source

The Flask application communicates with Ollama using its local API.

Source