Knowledge search ranks by how near a chunk's meaning is, not by its place in two lists

Fused by rank, a full-text match on a question's everyday words outvoted a
far nearer meaning: on the PoC, "how much leave do fathers get" found the
annual-leave page before the paternity one (cosine distance 0.44 against
0.25). Now a chunk scores its similarity to the question plus up to 0.3 for
a full-text match, each search brings four times k candidates, the text
search drops Turkish and English stop words, and an operator's search says
when the embedding model did not answer rather than quietly searching text.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

internal/control/adminapi/kb.go

@@ -450,11 +450,15 @@ func (a *API) kbSearch(w http.ResponseWriter, r *http.Request) {
 		k = 5
 	}
 	q := store.KBSearch{OrgID: c.OrgID, Collections: []store.KBCollection{c}, Text: in.Query, K: k}
-	// Without the model, the full-text half still answers.
+	// Said, not swallowed: a search that quietly lost its meaning half
+	// looks like a collection that does not know the answer.
 	if a.kb.Embed != nil {
-		if v, err := a.kb.Embed(r.Context(), c.EmbedModel, in.Query); err == nil {
-			q.Embeddings = map[string][]float32{c.EmbedModel: v}
+		v, err := a.kb.Embed(r.Context(), c.EmbedModel, in.Query)
+		if err != nil {
+			writeError(w, http.StatusBadGateway, c.EmbedModel+" did not embed the question: "+err.Error())
+			return
 		}
+		q.Embeddings = map[string][]float32{c.EmbedModel: v}
 	}
 	hits, err := a.kb.Store.SearchChunks(r.Context(), q)
 	if err != nil {