<?php
// chatbot/rag/search.php
class VectorSearch {
    private $vectors;
    private $dataFile;
    private $lastError = null;
    
    public function __construct() {
        $this->dataFile = __DIR__ . '/data/vectors.json';
        
        // GCS Sync (If local file missing)
        if (!file_exists($this->dataFile)) {
            require_once 'gcs_helper.php';
            try {
                $gcs = new GCSHelper();
                if ($gcs->getBucketName()) {
                    $gcs->download('chatbot/vectors.json', $this->dataFile);
                }
            } catch (Exception $e) {
                // Ignore download error, start with empty
                $this->lastError = "GCS Download Failed: " . $e->getMessage();
                error_log($this->lastError);
            }
        }

        if (file_exists($this->dataFile)) {
            // Increase memory limit for large JSON
            ini_set('memory_limit', '512M');
            $content = file_get_contents($this->dataFile);
            $this->vectors = json_decode($content, true);
            
            if ($this->vectors === null) {
                $this->lastError = "JSON Decode Error: " . json_last_error_msg();
                error_log("RAG Error: " . $this->lastError);
                $this->vectors = [];
            } else {
                // Success
            }
        } else {
            $this->lastError = "File Not Found: " . $this->dataFile;
            error_log("RAG Error: " . $this->lastError);
            $this->vectors = [];
        }
    }

    public function getLastError() {
        return $this->lastError;
    }
    
    // 코사인 유사도 계산
    private function cosineSimilarity($vecA, $vecB) {
        $dotProduct = 0;
        $normA = 0;
        $normB = 0;
        
        // 벡터 크기가 다르면 0 반환 (예외처리)
        if (count($vecA) !== count($vecB)) return 0;
        
        for ($i = 0; $i < count($vecA); $i++) {
            $dotProduct += $vecA[$i] * $vecB[$i];
            $normA += $vecA[$i] * $vecA[$i];
            $normB += $vecB[$i] * $vecB[$i];
        }
        
        if ($normA == 0 || $normB == 0) return 0;
        
        return $dotProduct / (sqrt($normA) * sqrt($normB));
    }
    
    public function getVectorCount() {
        return count($this->vectors);
    }

    public function search($query, $apiKey, $limit = 5) {
        // 1. 쿼리 임베딩
        $url = "https://generativelanguage.googleapis.com/v1beta/models/text-embedding-004:embedContent?key=" . $apiKey;
        $data = [
            'model' => 'models/text-embedding-004',
            'content' => ['parts' => [['text' => $query]]]
        ];
        
        $ch = curl_init($url);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
        curl_setopt($ch, CURLOPT_POST, true);
        curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
        curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);
        $response = curl_exec($ch);
        curl_close($ch);
        
        $responseData = json_decode($response, true);
        
        if (!isset($responseData['embedding']['values'])) {
             error_log("RAG embedding failed: " . json_encode($responseData));
             return [];
        }
        
        $queryVector = $responseData['embedding']['values'];
        
        // 2. 유사도 계산
        $scored = [];
        foreach ($this->vectors as $doc) {
            $score = $this->cosineSimilarity($queryVector, $doc['vector']);
            $doc['score'] = $score;
            // 벡터 데이터는 결과에서 제외 (용량 절약)
            unset($doc['vector']); 
            $scored[] = $doc;
        }
        
        // 3. 정렬 (유사도 내림차순)
        usort($scored, function($a, $b) {
            return $b['score'] <=> $a['score'];
        });
        
        // 4. 상위 N개 반환
        return array_slice($scored, 0, $limit);
    }
}
?>