WebAI StudioSemantic vs. Keyword Search
EmbeddingsSearch a help center by meaning, side by side with keyword search — and watch keywords miss what embeddings find.
Why On-Device?
On-device embeddings cost nothing per query, so you can afford to search on every keystroke — no network round trip, no per-call billing, and queries stay private.
Interactive Demo
Matches only entries sharing literal words with the query.
Build the index to enable semantic search.
Implementation Code
Keep exploring
56 demos, all running on-device.
Moderation Cascade
The production pattern for cheap moderation: embeddings clear the obvious 90% in microseconds, the LLM judges only the borderline.
Duplicate Detector
Catch near-duplicate bug reports before they are filed, even when they share no words with the original.
Cluster & Label
Group raw user feedback into themes with k-means over embeddings, then let the Prompt API name each cluster.