SciLifeLab Serve
A Django-based platform that lets life science researchers at a Swedish research institute serve machine learning models and host data science apps such as Shiny, Gradio, Streamlit, and Dash on a shared Kubernetes cluster.
SciLifeLab Serve is a platform offering machine learning model serving, data science app hosting, and web-based integrated development environments to life science researchers affiliated with SciLifeLab, a Swedish research institute. It is developed and operated by the SciLifeLab Data Centre and runs in production at serve.scilifelab.se.
This repository holds the main Django application, which uses the Kubernetes API to control resources on a dedicated cluster administered by KTH Royal Institute of Technology. It can also be deployed on a local machine and connected to a locally running Kubernetes cluster, using either Docker Compose or Rancher Desktop for local development, each with different trade-offs in setup complexity versus a full Kubernetes environment.
The main branch tracks the deployed production version, while develop and staging hold work in progress; contributions go through pull requests against develop.