/**
 * Recherche vectorielle sur les embeddings V2
 * Cosine similarity + top-K
 *
 * Utilisé par : server/api/chatbot-v2.post.ts
 * Données     : server/data/embeddings-v2.json (généré par scripts/vectorize-v2.js)
 */

import { readFileSync, existsSync } from 'fs'
import { fileURLToPath } from 'url'
import { resolve, dirname } from 'path'

// ── Types ──────────────────────────────────────────────────────────────────────

export interface EmbeddingEntry {
  fiche_id: string
  nom: string
  famille: number
  hashtags: string[]
  embedding: number[]
  text_preview: string
}

export interface SearchResult {
  fiche_id: string
  nom: string
  famille: number
  hashtags: string[]
  score: number
  text_preview: string
}

// ── Cosine similarity ──────────────────────────────────────────────────────────

export function cosineSimilarity(a: number[], b: number[]): number {
  if (a.length !== b.length) return 0
  let dot = 0, normA = 0, normB = 0
  for (let i = 0; i < a.length; i++) {
    dot += a[i] * b[i]
    normA += a[i] * a[i]
    normB += b[i] * b[i]
  }
  const denom = Math.sqrt(normA) * Math.sqrt(normB)
  return denom === 0 ? 0 : dot / denom
}

// ── Top-K search ───────────────────────────────────────────────────────────────

export function topKSearch(
  embeddings: EmbeddingEntry[],
  queryEmbedding: number[],
  k: number = 5
): SearchResult[] {
  return embeddings
    .map(e => ({
      fiche_id: e.fiche_id,
      nom: e.nom,
      famille: e.famille,
      hashtags: e.hashtags,
      score: cosineSimilarity(e.embedding, queryEmbedding),
      text_preview: e.text_preview
    }))
    .sort((a, b) => b.score - a.score)
    .slice(0, k)
}

// ── Chargement lazy des embeddings (cache module-level) ────────────────────────

let _embeddingsV2: EmbeddingEntry[] | null = null

export function loadEmbeddingsV2(): EmbeddingEntry[] {
  if (_embeddingsV2 !== null) return _embeddingsV2

  try {
    // Résolution du chemin depuis server/utils/ vers server/data/
    const currentDir = dirname(fileURLToPath(import.meta.url))
    const embPath = resolve(currentDir, '..', 'data', 'embeddings-v2.json')

    if (!existsSync(embPath)) {
      console.warn('[vectorSearch] embeddings-v2.json absent - V2 vector search désactivé')
      console.warn('[vectorSearch] Lancer : MISTRAL_API_KEY=xxx node scripts/vectorize-v2.js')
      _embeddingsV2 = []
      return []
    }

    const raw = readFileSync(embPath, 'utf-8')
    const data = JSON.parse(raw)
    _embeddingsV2 = data.embeddings ?? []
    console.log(`[vectorSearch] ${_embeddingsV2!.length} embeddings V2 chargés (${data.meta?.model ?? 'unknown'})`)
    return _embeddingsV2!
  } catch (e: any) {
    console.warn('[vectorSearch] Erreur chargement embeddings-v2.json :', e?.message ?? e)
    _embeddingsV2 = []
    return []
  }
}