SwissAI-Team7 / README.md
Iban Eguia Moraza
More documentation
08c856a unverified
|
raw
history blame
1.21 kB
metadata
title: Lighthouse
emoji: 📚
colorFrom: yellow
colorTo: yellow
sdk: docker
pinned: false
license: apache-2.0
short_description: We turn overwhelming diagnoses into clear, trusted guidance

This is the project submission for the Snackaton team in the Swiss AI weeks Hackaton Lausanne 2025.

Team Members

  • Iban Eguia
  • Mohamed Aziz Hamza
  • Javier Belmonte
  • África Santos
  • Deep Shah

Running

The web interface is dockerized used a fairly unmodified base image. It requires 2 environment variables:

  • OPENAI_API_KEY: Your OpenAI API key / Swiss AI platform API key
  • OPENAI_API_BASE_URL: Base URL to use when calling the model. For Apertus in Swiss AI platform, use https://api.swisscom.com/layer/swiss-ai-weeks/apertus-70b/v1

It is mainly tailored to run in the HuggingFace Spaces platform. You can create a new space and add this repository to it.

In case you want to run it locally, you can run this docker commands (replace with podman if you're using podman instead of docker):

docker build --tag 'lighthouse' .
docker run -d -p 7860:7860 -e OPENAI_API_KEY=<api_key> -e OPENAI_API_BASE_URL=<api_key> -v lighthouse:/data --name lighthouse --restart always lighthouse