Semantic/Hybrid Search in the Browser
bartdegoede
13 points
7 comments
July 11, 2026
Related Discussions
Found 5 related stories in 1259.8ms across 14,015 title embeddings via pgvector HNSW
- Omnisearch – A lightweight metasearch engine written in C bitbasher · 15 pts · May 15, 2026 · 55% similar
- Beyond Semantic Similarity 44za12 · 53 pts · May 12, 2026 · 53% similar
- Rethinking search as code generation 1zael · 69 pts · June 02, 2026 · 49% similar
- Google changes its search box berkeleyjunk · 461 pts · May 19, 2026 · 48% similar
- Full-Text Search with DuckDB ethagnawl · 111 pts · April 30, 2026 · 48% similar
Discussion Highlights (3 comments)
RestartKernel
This is very good. Super snappy and gives me what I'm looking for. Great write-up too. How much more would it cost to use a multilingual tokeniser? I realise this is somewhat pointless for an English blog, but services like Uber Eats have something like that going on (server-side of course, and they may just be translating queries).
rdksu
This is a very exciting field to make stuff in! I also experimented with a completely client side wallpaper search xD,a while back. In case some one is interested here is it : https://web-inky-ten-60.vercel.app/
docheinestages
Every browser should have an embedding API to avoid having to worry about the plumbing and data transfer.