Raki

Raki is a platform to extract structured information from medical reports of intervention and diagnostic procedures.

Setup

Option 1: Using Docker (Recommended)

1. Make sure you have Docker and Docker Compose installed on your system.

2. Start the application:

docker-compose up

This will start both the backend service (on port 8000) and the frontend service (on port 3000).

Option 2: Manual Setup

Backend Build (Required First)

Make sure you have Python 3.12+ installed.

1. Install uv:

pip install uv

2. Navigate to the backend directory:

cd projects/llm_backend/

3. Create a virtual environment and install dependencies:

uv venv
. .venv/bin/activate  # For Unix-like systems
# or
.\.venv\Scripts\activate  # For Windows
uv sync

4. Navigate to the backend app directory:

cd app

3. Create executable:

pyinstaller -F main.py --clean --hidden-import=pydantic --hidden-import=pydantic-core --hidden-import=pydantic.deprecated.decorator

4. Append OS-specific suffix to the executable in dist/ directory:

• Linux: -x86_64-unknown-linux-gnu
• macOS: -aarch64-apple-darwin
• Windows: -x86_64-pc-windows-msvc

Frontend Setup

1. Navigate to the frontend directory:

cd projects/frontend

2. Install dependencies:

yarn

3. Install Rust Make sure you have Rust installed on your system. You can install it from https://www.rust-lang.org/tools/install

4. Run the app:

For web development mode:

yarn dev

For desktop development mode:

yarn tauri dev

Backend Development Server (Optional)

1. Navigate to the backend directory:

cd projects/llm_backend

2. Create a virtual environment and install dependencies:

uv venv
. .venv/bin/activate  # For Unix-like systems
# or
.\.venv\Scripts\activate  # For Windows
uv sync

3. Run the development server:

uvicorn app.main:app --reload --port 8000

Building for Production

1. First build the backend executable (if not already done):

cd projects/llm_backend/app
pyinstaller -F main.py --clean --hidden-import=pydantic --hidden-import=pydantic-core --hidden-import=pydantic.deprecated.decorator

Don't forget to append the OS-specific suffix to the executable in dist/ directory.

2. Build the desktop application:

cd projects/frontend
yarn tauri build

The bundled application will be available in src-tauri/target/bundle

Development Resources

Excalidraw: https://excalidraw.com/#json=yQBFTY2Es-D9PvV2uUigK,-VK_8ZYhWF8_FpJjFTOC6A