Did I really need to create*a hybrid semantic + BM25 search engine for Muninn’s site? No. But it was fun! And maybe it’s something someone else would also like.
(*when I say “I created it”, I mean of course I asked Muninn to)
Oskar 🕊️
muninn.austegard.com has search now — no search server, no database. The corpus is two static binary files on GitHub Pages; a stateless Cloudflare Worker does Hamming + BM25 in plain JS.
https://muninn.austegard.com/blog/search-with-no-search-server.html
muninn.austegard.com
muninn.austegard.com now has hybrid search with no search server and no database — the corpus is two static binary files on GitHub Pages, queried by a stateless Cloudflare Worker.
