Fix Artgrid collector matching and split ranker

backend/services/ranker.go

@@ -0,0 +1,159 @@
+package services
+
+import (
+	"sort"
+	"strings"
+)
+
+type GeminiBatchStats struct {
+	CandidateCap     int      `json:"candidateCap"`
+	Requested        int      `json:"requested"`
+	Batches          int      `json:"batches"`
+	Succeeded        int      `json:"succeeded"`
+	Failed           int      `json:"failed"`
+	RecommendedCount int      `json:"recommendedCount"`
+	Errors           []string `json:"errors,omitempty"`
+}
+
+func RankSearchResults(query string, results []SearchResult) []SearchResult {
+	queryTerms := strings.Fields(strings.ToLower(query))
+	positiveTerms := []string{
+		"b-roll", "b roll", "stock", "stock footage", "footage", "cinematic", "editorial",
+		"establishing", "4k", "hd", "drone", "ambient", "scene", "urban", "cityscape",
+	}
+	negativeTerms := []string{
+		"shocking", "amazing", "crazy", "must watch", "reaction", "gossip", "celebrity",
+		"thumbnail", "meme", "prank", "drama", "breaking", "viral", "tutorial",
+		"how to", "review", "walkthrough", "course", "lesson", "podcast", "interview",
+		"premiere pro", "after effects", "explained", "breakdown", "vlog",
+	}
+	type scoredResult struct {
+		item  SearchResult
+		score int
+	}
+
+	scored := make([]scoredResult, 0, len(results))
+	for _, result := range results {
+		score := 0
+		text := strings.ToLower(result.Title + " " + result.Snippet + " " + result.Source)
+		for _, term := range queryTerms {
+			if strings.Contains(text, term) {
+				score += 3
+			}
+		}
+		for _, term := range positiveTerms {
+			if strings.Contains(text, term) {
+				score += 2
+			}
+		}
+		for _, term := range negativeTerms {
+			if strings.Contains(text, term) {
+				score -= 4
+			}
+		}
+		if result.ThumbnailURL != "" {
+			score += 2
+		}
+		if result.PreviewVideoURL != "" {
+			score += 3
+		}
+		switch result.Source {
+		case "Google Video":
+			score -= 1
+		case "Envato":
+			score += 7
+		case "Artgrid":
+			score += 7
+		}
+		scored = append(scored, scoredResult{item: result, score: score})
+	}
+
+	sort.SliceStable(scored, func(i, j int) bool {
+		return scored[i].score > scored[j].score
+	})
+
+	ranked := make([]SearchResult, 0, len(scored))
+	for _, item := range scored {
+		ranked = append(ranked, item.item)
+	}
+	return ranked
+}
+
+func GeminiCandidateLimit(total int) int {
+	switch {
+	case total <= 8:
+		return total
+	case total <= 16:
+		return 12
+	default:
+		return 16
+	}
+}
+
+func EvaluateAllCandidatesWithGemini(service *GeminiService, query string, ranked []SearchResult) ([]AIRecommendation, GeminiBatchStats) {
+	const chunkSize = 8
+	limit := GeminiCandidateLimit(len(ranked))
+	stats := GeminiBatchStats{
+		CandidateCap: limit,
+		Requested:    min(limit, len(ranked)),
+	}
+	merged := make([]AIRecommendation, 0, len(ranked))
+	seen := map[string]bool{}
+	for start := 0; start < limit; start += chunkSize {
+		end := start + chunkSize
+		if end > limit {
+			end = limit
+		}
+		batch := ranked[start:end]
+		stats.Batches++
+		recommended, err := service.Recommend(query, batch)
+		if err != nil {
+			stats.Failed++
+			if len(stats.Errors) < 5 {
+				stats.Errors = append(stats.Errors, err.Error())
+			}
+			continue
+		}
+		stats.Succeeded++
+		for _, item := range recommended {
+			if item.Link == "" || seen[item.Link] {
+				continue
+			}
+			seen[item.Link] = true
+			merged = append(merged, item)
+		}
+	}
+	stats.RecommendedCount = len(merged)
+	return merged, stats
+}
+
+func MergeRecommendations(recommended []AIRecommendation, ranked []SearchResult, limit int) []AIRecommendation {
+	merged := make([]AIRecommendation, 0, min(limit, len(ranked)))
+	seen := map[string]bool{}
+
+	for _, item := range recommended {
+		if item.Link == "" || seen[item.Link] {
+			continue
+		}
+		seen[item.Link] = true
+		merged = append(merged, item)
+	}
+
+	for _, item := range ranked {
+		if len(merged) >= limit || item.Link == "" || seen[item.Link] {
+			continue
+		}
+		seen[item.Link] = true
+		merged = append(merged, AIRecommendation{
+			Title:           item.Title,
+			Link:            item.Link,
+			Snippet:         item.Snippet,
+			ThumbnailURL:    item.ThumbnailURL,
+			PreviewVideoURL: item.PreviewVideoURL,
+			Source:          item.Source,
+			Reason:          "Keyword-ranked result added without extra Gemini vision tokens.",
+			Recommended:     true,
+		})
+	}
+	return merged
+}