Hubert Thieblot
@hthieblot
参加 September 2007
2.8K フォロー中 61.8K ファン
this is actually how ai search should work
Today we’re launching WonderSearch (YC F26)
Search millions of unstructured documents without pre-embedding the corpus. With comparable/better retrieval recall than embedding-based search.
WonderSearch searches at query time:
> No corpus-wide embedding step.
> No vector index to maintain.
> More compute only when needed.
> Pay per search intead of embeddings you may never use.
Go from raw data to useful answers in seconds.
Link + FAQ below (+ free launch credits!) ↓
もっと見る
