How I do use the recent llama.cpp native tools to do web rag a.k.a. web_fetch (or anything else for the matter) directly from inside the llama-server's webui

As some other fellow lllmers I've discovered few days ago that the amazing llama.cpp project has just added native tools functionalities into the server. After having enabled the relative options into llama-server and played a bit with the most harmless of them all, get_datetime, I've bit the bullet