Fix Artgrid collector matching and split ranker

2026-03-13 19:31:57 +09:00
parent 5aebbef639
commit e4262613c3
6 changed files with 250 additions and 165 deletions
@@ -11,7 +11,6 @@ import (
 	"os/exec"
 	"path/filepath"
 	"regexp"
-	"sort"
 	"strings"
 	"sync"
 	"time"
@@ -87,16 +86,6 @@ type searchDebugSummary struct {
 	GeminiCandidateCap int              `json:"geminiCandidateCap,omitempty"`
 }

-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 RegisterRoutes(router *gin.Engine, app *App) {
 	router.GET("/healthz", func(c *gin.Context) {
 		c.JSON(http.StatusOK, gin.H{"status": "ok"})
@@ -329,10 +318,10 @@ func (a *App) searchMedia(c *gin.Context) {
 	if len(queryVariants) > 0 {
 		rankQuery = strings.Join(queryVariants[:min(len(queryVariants), 3)], " ")
 	}
-	scored := rankSearchResults(rankQuery, results)
-	a.debug("search ranked summary", summarizeSearchResults(scored, time.Since(started), geminiCandidateLimit(len(scored)), ""))
+	scored := services.RankSearchResults(rankQuery, results)
+	a.debug("search ranked summary", summarizeSearchResults(scored, time.Since(started), services.GeminiCandidateLimit(len(scored)), ""))
 	a.Hub.Broadcast("progress", gin.H{"type": "search", "status": "analyzing top candidate visuals with Gemini Vision", "progress": 75})
-	recommended, geminiStats := evaluateAllCandidatesWithGemini(a.GeminiService, req.Query, scored)
+	recommended, geminiStats := services.EvaluateAllCandidatesWithGemini(a.GeminiService, req.Query, scored)
 	a.debug("search gemini evaluation", geminiStats)
 	err = nil
 	if len(recommended) == 0 {
@@ -359,7 +348,7 @@ func (a *App) searchMedia(c *gin.Context) {
 		return
 	}

-	merged := mergeRecommendations(recommended, scored, 20)
+	merged := services.MergeRecommendations(recommended, scored, 20)
 	a.debug("search complete summary", summarizeRecommendationResults(merged, time.Since(started), ""))
 	response := gin.H{"results": merged, "queries": queryVariants}
 	a.Hub.Broadcast("progress", gin.H{"type": "search", "status": "search complete", "progress": 100})
@@ -438,149 +427,6 @@ func selectedPlatformLabel(platforms map[string]bool) string {
 	return strings.Join(labels, ", ")
 }

-func evaluateAllCandidatesWithGemini(service *services.GeminiService, query string, ranked []services.SearchResult) ([]services.AIRecommendation, geminiBatchStats) {
-	const chunkSize = 8
-	limit := geminiCandidateLimit(len(ranked))
-	stats := geminiBatchStats{
-		CandidateCap: limit,
-		Requested:    min(limit, len(ranked)),
-	}
-	merged := make([]services.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 rankSearchResults(query string, results []services.SearchResult) []services.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  services.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([]services.SearchResult, 0, len(scored))
-	for _, item := range scored {
-		ranked = append(ranked, item.item)
-	}
-	return ranked
-}
-
-func mergeRecommendations(recommended []services.AIRecommendation, ranked []services.SearchResult, limit int) []services.AIRecommendation {
-	merged := make([]services.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, services.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
-}
-
-func geminiCandidateLimit(total int) int {
-	switch {
-	case total <= 8:
-		return total
-	case total <= 16:
-		return 12
-	default:
-		return 16
-	}
-}
-
 func summarizeSearchResults(results []services.SearchResult, duration time.Duration, geminiCap int, warning string) searchDebugSummary {
 	bySource := map[string]int{}
 	withPreview := 0