Start the open-webui server with ollama in the same docker image:
docker run -d -p 3000:8080 -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui3 --restart always ghcr.io/open-webui/open-webui:ollama
Now add a GenAI model from https://ollama.com/search. For example to add Mistral run