Klemmari

Built With

How to Run

1. Install the latest LTS version of Node.js from the official website.
2. Clone the repository to your local machine.
3. Navigate to the project directory and install the dependencies for the frontend:

   npm install

4. Install the Python dependencies:

   pip install -r requirements.txt

5. Create a .env file in the root directory and fill it according to .env.example:

   cp .env.example .env

6. Start the Vite development server to access the frontend:

   npm run dev

7. Open another terminal to start the Flask-server:

    python src/Azure.py

About the Website

Klemmari is a web application designed to simulate a patient information system. The website features an AI-powered chatbot that helps users by answering questions and providing assistance with navigating the site. The AI is powered by the GPT-4o model and is built using a Retrieval-Augmented Generation (RAG) architecture, which enhances its ability to retrieve relevant information and generate contextually appropriate responses.

Known bugs

Language model / default prompt still need some optimizing since chatbot doesn't always understand the user's question