#!/usr/bin/env node
/**
 * Embedding Proof-of-Concept Script
 *
 * Demonstrates how category embeddings work for product matching.
 * Uses OpenAI text-embedding-3-small model.
 *
 * Usage: node scripts/embedding-poc.js
 */

const path = require('path');
require('dotenv').config({ path: path.join(__dirname, '../.env') });

const { getDbConnection, closeAllConnections } = require('../src/utils/dbConnection');

// ============================================================================
// Configuration
// ============================================================================

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const EMBEDDING_MODEL = 'text-embedding-3-small';
const EMBEDDING_DIMENSIONS = 1536;

// Sample products to test (you can modify these)
const TEST_PRODUCTS = [
  {
    name: "Cosmos Infinity Chipboard - Stamperia",
    description: "Laser-cut chipboard shapes featuring celestial designs for mixed media projects"
  },
  {
    name: "Distress Oxide Ink Pad - Mermaid Lagoon",
    description: "Water-reactive dye ink that creates an oxidized effect"
  },
  {
    name: "Hedwig Puffy Stickers - Paper House Productions",
    description: "3D puffy stickers featuring Harry Potter's owl Hedwig"
  },
  {
    name: "Black Velvet Watercolor Brush Size 6",
    description: "Round brush for watercolor painting with synthetic bristles"
  },
  {
    name: "Floral Washi Tape Set",
    description: "Decorative paper tape with flower patterns, pack of 6 rolls"
  }
];

// ============================================================================
// OpenAI Embedding Functions
// ============================================================================

async function getEmbeddings(texts) {
  const response = await fetch('https://api.openai.com/v1/embeddings', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': `Bearer ${OPENAI_API_KEY}`
    },
    body: JSON.stringify({
      input: texts.map(t => t.substring(0, 8000)), // Max 8k chars per text
      model: EMBEDDING_MODEL,
      dimensions: EMBEDDING_DIMENSIONS
    })
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(`OpenAI API error: ${error.error?.message || response.status}`);
  }

  const data = await response.json();

  // Sort by index to ensure order matches input
  const sorted = data.data.sort((a, b) => a.index - b.index);

  return {
    embeddings: sorted.map(item => item.embedding),
    usage: data.usage,
    model: data.model
  };
}

// ============================================================================
// Vector Math
// ============================================================================

function cosineSimilarity(a, b) {
  let dotProduct = 0;
  let normA = 0;
  let normB = 0;

  for (let i = 0; i < a.length; i++) {
    dotProduct += a[i] * b[i];
    normA += a[i] * a[i];
    normB += b[i] * b[i];
  }

  return dotProduct / (Math.sqrt(normA) * Math.sqrt(normB));
}

function findTopMatches(queryEmbedding, categoryEmbeddings, topK = 10) {
  const scored = categoryEmbeddings.map(cat => ({
    ...cat,
    similarity: cosineSimilarity(queryEmbedding, cat.embedding)
  }));

  scored.sort((a, b) => b.similarity - a.similarity);

  return scored.slice(0, topK);
}

// ============================================================================
// Database Functions
// ============================================================================

async function fetchCategories(connection) {
  console.log('\n📂 Fetching categories from database...');

  // Fetch hierarchical categories (types 10-13)
  const [rows] = await connection.query(`
    SELECT
      cat_id,
      name,
      master_cat_id,
      type
    FROM product_categories
    WHERE type IN (10, 11, 12, 13)
    ORDER BY type, name
  `);

  console.log(`   Found ${rows.length} category records`);

  // Build category paths
  const byId = new Map(rows.map(r => [r.cat_id, r]));
  const categories = [];

  for (const row of rows) {
    const path = [];
    let current = row;

    // Walk up the tree to build full path
    while (current) {
      path.unshift(current.name);
      current = current.master_cat_id ? byId.get(current.master_cat_id) : null;
    }

    categories.push({
      id: row.cat_id,
      name: row.name,
      type: row.type,
      fullPath: path.join(' > '),
      embeddingText: path.join(' ') // For embedding generation
    });
  }

  // Count by level
  const levels = {
    10: categories.filter(c => c.type === 10).length,
    11: categories.filter(c => c.type === 11).length,
    12: categories.filter(c => c.type === 12).length,
    13: categories.filter(c => c.type === 13).length,
  };

  console.log(`   Level breakdown: ${levels[10]} top-level, ${levels[11]} L2, ${levels[12]} L3, ${levels[13]} L4`);

  return categories;
}

// ============================================================================
// Main Script
// ============================================================================

async function main() {
  console.log('═══════════════════════════════════════════════════════════════');
  console.log('  EMBEDDING PROOF-OF-CONCEPT');
  console.log('  Model: ' + EMBEDDING_MODEL);
  console.log('═══════════════════════════════════════════════════════════════');

  if (!OPENAI_API_KEY) {
    console.error('❌ OPENAI_API_KEY not found in environment');
    process.exit(1);
  }

  let connection;

  try {
    // Step 1: Connect to database
    console.log('\n🔌 Connecting to database via SSH tunnel...');
    const { connection: conn } = await getDbConnection();
    connection = conn;
    console.log('   ✅ Connected');

    // Step 2: Fetch categories
    const categories = await fetchCategories(connection);

    // Step 3: Generate embeddings for categories
    console.log('\n🧮 Generating embeddings for categories...');
    console.log('   This will cost approximately $' + (categories.length * 0.00002).toFixed(4));

    const startTime = Date.now();

    // Process in batches of 100 (OpenAI limit is 2048)
    const BATCH_SIZE = 100;
    let totalTokens = 0;

    for (let i = 0; i < categories.length; i += BATCH_SIZE) {
      const batch = categories.slice(i, i + BATCH_SIZE);
      const texts = batch.map(c => c.embeddingText);

      const result = await getEmbeddings(texts);

      // Attach embeddings to categories
      for (let j = 0; j < batch.length; j++) {
        batch[j].embedding = result.embeddings[j];
      }

      totalTokens += result.usage.total_tokens;
      console.log(`   Batch ${Math.floor(i / BATCH_SIZE) + 1}/${Math.ceil(categories.length / BATCH_SIZE)}: ${batch.length} categories embedded`);
    }

    const embeddingTime = Date.now() - startTime;
    console.log(`   ✅ Generated ${categories.length} embeddings in ${embeddingTime}ms`);
    console.log(`   📊 Total tokens used: ${totalTokens} (~$${(totalTokens * 0.00002).toFixed(4)})`);

    // Step 4: Test with sample products
    console.log('\n═══════════════════════════════════════════════════════════════');
    console.log('  TESTING WITH SAMPLE PRODUCTS');
    console.log('═══════════════════════════════════════════════════════════════');

    for (const product of TEST_PRODUCTS) {
      console.log('\n┌─────────────────────────────────────────────────────────────');
      console.log(`│ Product: "${product.name}"`);
      console.log(`│ Description: "${product.description.substring(0, 60)}..."`);
      console.log('├─────────────────────────────────────────────────────────────');

      // Generate embedding for product
      const productText = `${product.name} ${product.description}`;
      const { embeddings: [productEmbedding] } = await getEmbeddings([productText]);

      // Find top matches
      const matches = findTopMatches(productEmbedding, categories, 10);

      console.log('│ Top 10 Category Matches:');
      matches.forEach((match, i) => {
        const similarity = (match.similarity * 100).toFixed(1);
        const bar = '█'.repeat(Math.round(match.similarity * 20));
        const marker = i < 3 ? ' ✅' : '';
        console.log(`│  ${(i + 1).toString().padStart(2)}. [${similarity.padStart(5)}%] ${bar.padEnd(20)} ${match.fullPath}${marker}`);
      });
      console.log('└─────────────────────────────────────────────────────────────');
    }

    // Step 5: Summary
    console.log('\n═══════════════════════════════════════════════════════════════');
    console.log('  SUMMARY');
    console.log('═══════════════════════════════════════════════════════════════');
    console.log(`  Categories embedded: ${categories.length}`);
    console.log(`  Embedding time: ${embeddingTime}ms (one-time cost)`);
    console.log(`  Per-product lookup: ~${(Date.now() - startTime) / TEST_PRODUCTS.length}ms`);
    console.log(`  Vector dimensions: ${EMBEDDING_DIMENSIONS}`);
    console.log(`  Memory usage: ~${(categories.length * EMBEDDING_DIMENSIONS * 4 / 1024 / 1024).toFixed(2)} MB (in-memory vectors)`);
    console.log('');
    console.log('  💡 In production:');
    console.log('     - Category embeddings are computed once and cached');
    console.log('     - Only product embedding is computed per-request (~$0.00002)');
    console.log('     - Vector search is instant (in-memory cosine similarity)');
    console.log('     - Top 10 results go to AI for final selection (~$0.0001)');
    console.log('═══════════════════════════════════════════════════════════════\n');

  } catch (error) {
    console.error('\n❌ Error:', error.message);
    if (error.stack) {
      console.error(error.stack);
    }
    process.exit(1);
  } finally {
    await closeAllConnections();
    console.log('🔌 Database connections closed');
  }
}

// Run the script
main();