Medtrack

Blog post | Screenshots

Upload a picture of a medication and get the essential information.

Caution

Medical Disclaimer: This project is for educational and technical demonstration purposes only. The information provided by the AI should not be used for medical diagnosis, treatment, or as a substitute for professional medical advice. Always consult a healthcare professional for medication concerns.

Note

This repository was built as a personal exploration to experiment with new technologies and does not represent a production-ready medical tool.

Prerequisites

• uv (Python package manager)

• Python 3.12+

• Refer to Ollama download page to download Ollama according to your operating system

• Setup your local model

Ollama Model Setup

1.Pull a Small model from ollama

ollama pull llama3.2:3b

2.Setup a Modelfile with a customized prompt**

See Modelfile used in this project.

Getting Started

1.Clone the repository

git clone https://github.com/hoochlef/medtrack
cd medtrack

2.Sync dependencies

This command creates a virtual environment and installs all dependencies automatically.

uv sync

For the folks that don't use uv, there's a requirements.txt file at the root of the project.

3.Environment Setup

Copy the example environment file and update your variables.

cp .env.example .env

4.Start Development Server

uv run python manage.py runserver

Tech Stack

• Framework: Django 5.2.8
• Smart tools (ML tools): paddleocr, ollama
• Dev tools: uv, ruff
• Other: check dependencies

License

This repository is licensed under the MIT License