simhealth

Using LLMs to treat healthcare induced anxiety

Run on Docker

Run the following command

docker-compose up --build

Dev Instructions

Install

Make sure you have python 3 installed (specifically 3.12.11)

Install Ollama. This is needed for running an LLM locally.

Once you have ollama installed and running. Run the following command in the terminal. This downloads the gemma3:1b model

ollama pull gemma3:1b

Create venv

python3.12 -m venv .venv

Activate venv

.venv/bin/activate

Backend Setup

1. Install dependencies:

pip install -r requirements.txt

2. Start the backend server:

cd src
uvicorn server:app --host 0.0.0.0 --port 8000

Frontend Setup

In a separate terminal

1. Install dependencies:

cd ui
npm install

2. Configure proxy in vite.config.js (already done):

server: {
  proxy: {
    '/api': 'http://localhost:8000'
  }
}

3. Start development server:

npm run dev