7th July 2026
ternlight · semantic search · React docs
An embedding model in 7 MB.
Runs on your CPU. No API.
Drop it in, embed text in milliseconds, and never call a server.
Runs in your browser
This is a really interesting project. A very small model which can be run in the browser to give you semantic search. Indexing can be done server side to cut down on loading too.