Vector demo, exact kNN, live
Full-precision float-cosine scan over every stored vector: it recovers 100% of the true neighbours (recall 1.0), no index to build and no recall cliff. At this corpus size exact brute-force beats approximate HNSW on both recall and speed. Measured live.
the vector-DB leader
RECALL CLIFF. An approximate HNSW index trades recall for speed: it returns the wrong neighbours some fraction of the time, and you must build the graph index before the first query.
semurg, one engine
100% recall@10, zero index. The exact float-cosine topK over every stored vector IS the ground truth, so no neighbour is ever missed, and there is nothing to build first.
It beats the approximate index on recall AND speed, with no index at all.
GloVe-6B-100d. Measured live on this box. Download it from Stanford NLP and re-run it yourself.
ask the agent to "search", the exact-scan recall and QPS render here
Honest: the headline is the EXACT scan (recall 1.0), the number an approximate vector index can't match without giving up recall. The 512-bit binary code is a separate, optional density lever (6x denser at ~66% recall) for very large corpora, and it runs in the same engine that also serves graph, search and key-value.