Project Overview

My friend is a freelance lawyer who handles sensitive client contracts. She needed to use AI to quickly find information in long documents, but could not upload them to Cloud services like ChatGPT due to confidentiality rules. To solve this, I built LocalDoc Assistant - a private AI tool that reads her documents and answers questions about them, completely offline. Her data never leaves her laptop.

Demo

A screenshot demonstrates the app correctly answering "When is my birthday?" from an uploaded text file with zero internet access. The implementation is available at https://github.com/vaibhav7549/localdoc-assistant.

How I Built It

The project was constructed using several key components:

• Model: Ollama running Google's Gemma 2 (2B) open-weight model locally on the laptop
• Interface: Streamlit, an open-source Python framework
• PDF Reading: PyPDF2 for handling PDF files

All AI inference runs entirely on the local machine. There are no API keys, no cloud calls, and no data ever leaves the computer.

Why Open Innovation Matters

This project would have been impossible with a closed API. The core value lies in privacy - my friend cannot upload client documents to a third-party server. Open-source AI enabled this because:

• Privacy: The model runs locally. No data is transmitted anywhere.
• Zero cost: No API subscriptions or per-token fees.
• Customizable: She can swap in a larger model later if better accuracy is needed, without changing any code.

Prize Category

Best Use of Gemma

Thanks for reading! Built with ❤️ for a friend who values privacy.