This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

I built NoteWise AI, a local-first AI study assistant designed to help students study more efficiently using their own notes.

Students often have to go through lengthy PDFs and lecture notes to prepare for exams. NoteWise AI aims to make this process easier by allowing students to upload their notes and use AI to:

Generate short summaries and exam-oriented revision notes.

Ask questions about their study material.

Generate practice quizzes and answer keys.

Download generated summaries and quizzes for revision.

The initial version supports text-based PDF and TXT files.

The project is intended for students, independent learners, and tutors. In the future, it could become a low-cost study tool for students who want useful AI features without paying for an expensive subscription.>

Code

ANILION-CODE / NoteWise_AI

A local first study assistant that uses an open*weight language model through Ollama to summarize notes, answer questions from uploaded material, and generate practice quizzes.

NoteWise AI

A local first study assistant that uses an open*weight language model through Ollama to summarize notes, answer questions from uploaded material, and generate practice quizzes.

Features

• Upload selectable*text PDF or TXT notes
• Generate short, detailed, or exam revision summaries
• Ask questions using a lightweight keyword*based context selector
• Generate practice quizzes and download results as Markdown
• Run inference through Ollama on your own computer

Requirements

• Windows 10/11
• Python 3.10 or newer
• Ollama for Windows
• Enough RAM to run the model you choose

Run locally

1. Install Python from https://www.python.org/downloads/ if you do not already have it.

2. Install Ollama from https://ollama.com/download.

3. Open Command Prompt or PowerShell and download the default model:

   ollama run llama3.2:3b

   Wait for the model to download. When the model prompt appears, you can type /bye to exit. Leave Ollama running in the background.

4. Extract this repository, open a terminal in the notewise_ai folder, and…

View on GitHub

How I Built It

I built NoteWise AI using Python and Streamlit, with Ollama providing access to a locally running open-weight language model.

The main technologies are:

Python: Application logic and document processing.

Streamlit: Browser-based user interface.

Ollama: Runs the language model locally.

Llama 3.2 3B: The default model configuration for generating summaries, answers, and quizzes.

pypdf: Extracts text from PDF documents.

Lightweight keyword retrieval: Selects relevant text from notes when answering questions.

The application sends prompts to the local Ollama service instead of relying on a hosted AI API. The initial version uses a simple retrieval approach, which I plan to improve with embeddings, vector search, and source references.

Why Does Open Innovation Matter?

Open innovation is important to NoteWise AI because students should have more choices in how they use AI tools and where their data is processed.

Using an open-weight model through Ollama makes local inference possible. In the intended local setup, study documents and prompts can remain on the user's computer rather than being sent to a third-party AI API.

It also gives the project flexibility. Developers can inspect and modify the code, experiment with compatible models, and improve retrieval or prompting for different subjects.

Running a model locally can reduce recurring per-request API charges, although hardware, electricity, and setup still have costs. This could make NoteWise AI useful for students who want to avoid depending on paid AI subscriptions.

The goal is to build a tool that users can understand, adapt, and improve instead of locking the entire application to one proprietary AI provider.