image search test

services/scanService.go

@@ -480,15 +480,33 @@ func scoreCachedHits(cached []repositories.CatalogueHit) []scoredHit {
 	return hits
 }
 
+// sortHits ranks by blended score, then by the model's own similarity, and
+// only then by name. Name alone used to break every tie, which quietly made
+// punctuation decide relevance: "Parle Monaco Classic" sorts above "Parle-G
+// Original …" because a space precedes a hyphen in ASCII, so equal-scoring
+// crackers beat the biscuit that was actually scanned.
 func sortHits(hits []scoredHit) {
 	sort.SliceStable(hits, func(i, j int) bool {
 		if hits[i].score != hits[j].score {
 			return hits[i].score > hits[j].score
 		}
+		di, dj := vectorRank(hits[i].Distance), vectorRank(hits[j].Distance)
+		if di != dj {
+			return di < dj
+		}
 		return hits[i].ProductName < hits[j].ProductName
 	})
 }
 
+// vectorRank orders by cosine distance, nearest first, with a row the model
+// never saw (-1, text-only) sorting behind every row it did.
+func vectorRank(d float64) float64 {
+	if d < 0 {
+		return math.MaxFloat64
+	}
+	return d
+}
+
 func (s *scanService) modelName() string {
 	if s.embedder == nil {
 		return "none"
@@ -516,8 +534,20 @@ func textScore(h repositories.CatalogueHit, label string, tokens []string) float
 	name := strings.ToLower(h.ProductName)
 	hay := name + " " + strings.ToLower(h.Title)
 	label = strings.ToLower(strings.TrimSpace(label))
-	if label != "" && strings.Contains(name, label) {
-		return 0.95
+	// The substring test compares separator-folded forms, so the brand's own
+	// punctuation does not decide the match: "Parle G", "Parle-G" and
+	// "ParleG" all have to reach "Parle-G Original Glucose Biscuits".
+	if label != "" {
+		foldedName, foldedLabel := utils.FoldSeparators(name), utils.FoldSeparators(label)
+		if foldedLabel != "" && strings.Contains(foldedName, foldedLabel) {
+			return 0.95
+		}
+		// Separators dropped rather than folded. Only for a label long enough
+		// that a run of letters means something — "lay" inside "malayalam" is
+		// not a match anyone wants.
+		if tight := utils.TightenLabel(label); len(tight) >= 4 && strings.Contains(utils.TightenLabel(name), tight) {
+			return 0.95
+		}
 	}
 	if len(tokens) == 0 {
 		return 0