Voice search, image search, and the assistant
Search by voice, search by image, and a grounded AI assistant with citations — all served through the tenant API's proxy layer.
Three new ways to search landed together: voice search (transcribe with Workers AI, then search by the transcript), image search (upload an image, get a caption and embedding, then search by meaning), and the AI assistant — a retrieval-augmented chat that cites the documents it draws its answer from, with conversation memory and streaming responses. Search rules also picked up exclusion filters and a zero-hits fallback, so a query with no matches can fall back to a recommendation model instead of an empty page.