ht-docker-ai/test/test.invoices.qwen3vl.ts

/**
 * Invoice extraction using Qwen3-VL 8B Vision (Direct)
 *
 * Multi-query approach: 5 parallel simple queries to avoid token exhaustion.
 * Single pass, no consensus voting.
 */
import { tap, expect } from '@git.zone/tstest/tapbundle';
import * as fs from 'fs';
import * as path from 'path';
import { execSync } from 'child_process';
import * as os from 'os';
import { ensureMiniCpm } from './helpers/docker.js';

const OLLAMA_URL = 'http://localhost:11434';
const VISION_MODEL = 'qwen3-vl:8b';

interface IInvoice {
  invoice_number: string;
  invoice_date: string;
  vendor_name: string;
  currency: string;
  net_amount: number;
  vat_amount: number;
  total_amount: number;
}

/**
 * Convert PDF to PNG images using ImageMagick
 */
function convertPdfToImages(pdfPath: string): string[] {
  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pdf-convert-'));
  const outputPattern = path.join(tempDir, 'page-%d.png');

  try {
    // 150 DPI is sufficient for invoice extraction, reduces context size
    execSync(
      `convert -density 150 -quality 90 "${pdfPath}" -background white -alpha remove "${outputPattern}"`,
      { stdio: 'pipe' }
    );

    const files = fs.readdirSync(tempDir).filter((f) => f.endsWith('.png')).sort();
    const images: string[] = [];

    for (const file of files) {
      const imagePath = path.join(tempDir, file);
      const imageData = fs.readFileSync(imagePath);
      images.push(imageData.toString('base64'));
    }

    return images;
  } finally {
    fs.rmSync(tempDir, { recursive: true, force: true });
  }
}

/**
 * Query Qwen3-VL for a single field
 * Uses simple prompts to minimize thinking tokens
 */
async function queryField(images: string[], question: string): Promise<string> {
  const response = await fetch(`${OLLAMA_URL}/api/chat`, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      model: VISION_MODEL,
      messages: [{
        role: 'user',
        content: `${question} Reply with just the value, nothing else.`,
        images: images,
      }],
      stream: false,
      options: {
        num_predict: 500,
        temperature: 0.1,
      },
    }),
  });

  if (!response.ok) {
    throw new Error(`Ollama API error: ${response.status}`);
  }

  const data = await response.json();
  return (data.message?.content || '').trim();
}

/**
 * Extract invoice data using multiple simple queries
 * Each query asks for 1-2 fields to minimize thinking tokens
 * (Qwen3's thinking mode uses all tokens on complex prompts)
 */
async function extractInvoiceFromImages(images: string[]): Promise<IInvoice> {
  console.log(`    [Vision] Processing ${images.length} page(s) with Qwen3-VL (multi-query)`);

  // Query each field separately to avoid excessive thinking tokens
  // Use explicit questions to avoid confusion between similar fields
  // Log each result as it comes in (not waiting for all to complete)
  const queryAndLog = async (name: string, question: string): Promise<string> => {
    const result = await queryField(images, question);
    console.log(`    [Query] ${name}: "${result}"`);
    return result;
  };

  const [invoiceNum, invoiceDate, vendor, currency, totalAmount, netAmount, vatAmount] = await Promise.all([
    queryAndLog('Invoice Number', 'What is the INVOICE NUMBER (not VAT number, not customer ID)? Look for "Invoice No", "Invoice #", "Rechnung Nr", "Facture". Just the number/code.'),
    queryAndLog('Invoice Date  ', 'What is the INVOICE DATE (not due date, not delivery date)? The date the invoice was issued. Format: YYYY-MM-DD'),
    queryAndLog('Vendor        ', 'What company ISSUED this invoice (the seller/vendor, not the buyer)? Look at the letterhead or "From" section.'),
    queryAndLog('Currency      ', 'What CURRENCY is used? Look for € (EUR), $ (USD), or £ (GBP). Answer with 3-letter code: EUR, USD, or GBP'),
    queryAndLog('Total Amount  ', 'What is the TOTAL AMOUNT INCLUDING TAX (the final amount to pay, with VAT/tax included)? Just the number, e.g. 24.99'),
    queryAndLog('Net Amount    ', 'What is the NET AMOUNT (subtotal before VAT/tax)? Just the number, e.g. 20.99'),
    queryAndLog('VAT Amount    ', 'What is the VAT/TAX AMOUNT? Just the number, e.g. 4.00'),
  ]);

  // Parse amount from string (handles European format)
  const parseAmount = (s: string): number => {
    if (!s) return 0;
    // Extract number from the response
    const match = s.match(/([\d.,]+)/);
    if (!match) return 0;
    const numStr = match[1];
    // Handle European format: 1.234,56 → 1234.56
    const normalized = numStr.includes(',') && numStr.indexOf(',') > numStr.lastIndexOf('.')
      ? numStr.replace(/\./g, '').replace(',', '.')
      : numStr.replace(/,/g, '');
    return parseFloat(normalized) || 0;
  };

  // Extract invoice number from potentially verbose response
  const extractInvoiceNumber = (s: string): string => {
    let clean = s.replace(/\*\*/g, '').replace(/`/g, '').trim();
    // Look for common invoice number patterns
    const patterns = [
      /\b([A-Z]{2,3}\d{10,})\b/i,           // IEE2022006460244
      /\b([A-Z]\d{8,})\b/i,                  // R0014359508
      /\b(INV[-\s]?\d{4}[-\s]?\d+)\b/i,     // INV-2024-001
      /\b(\d{7,})\b/,                        // 1579087430
    ];
    for (const pattern of patterns) {
      const match = clean.match(pattern);
      if (match) return match[1];
    }
    return clean.replace(/[^A-Z0-9-]/gi, '').trim() || clean;
  };

  // Extract date (YYYY-MM-DD) from response
  const extractDate = (s: string): string => {
    let clean = s.replace(/\*\*/g, '').replace(/`/g, '').trim();
    const isoMatch = clean.match(/(\d{4}-\d{2}-\d{2})/);
    if (isoMatch) return isoMatch[1];
    return clean.replace(/[^\d-]/g, '').trim();
  };

  // Extract currency
  const extractCurrency = (s: string): string => {
    const upper = s.toUpperCase();
    if (upper.includes('EUR') || upper.includes('€')) return 'EUR';
    if (upper.includes('USD') || upper.includes('$')) return 'USD';
    if (upper.includes('GBP') || upper.includes('£')) return 'GBP';
    return 'EUR';
  };

  return {
    invoice_number: extractInvoiceNumber(invoiceNum),
    invoice_date: extractDate(invoiceDate),
    vendor_name: vendor.replace(/\*\*/g, '').replace(/`/g, '').trim() || '',
    currency: extractCurrency(currency),
    net_amount: parseAmount(netAmount),
    vat_amount: parseAmount(vatAmount),
    total_amount: parseAmount(totalAmount),
  };
}

/**
 * Normalize date to YYYY-MM-DD
 */
function normalizeDate(dateStr: string | null): string {
  if (!dateStr) return '';
  if (/^\d{4}-\d{2}-\d{2}$/.test(dateStr)) return dateStr;

  const monthMap: Record<string, string> = {
    JAN: '01', FEB: '02', MAR: '03', APR: '04', MAY: '05', JUN: '06',
    JUL: '07', AUG: '08', SEP: '09', OCT: '10', NOV: '11', DEC: '12',
  };

  let match = dateStr.match(/^(\d{1,2})-([A-Z]{3})-(\d{4})$/i);
  if (match) {
    return `${match[3]}-${monthMap[match[2].toUpperCase()] || '01'}-${match[1].padStart(2, '0')}`;
  }

  match = dateStr.match(/^(\d{1,2})[\/.](\d{1,2})[\/.](\d{4})$/);
  if (match) {
    return `${match[3]}-${match[2].padStart(2, '0')}-${match[1].padStart(2, '0')}`;
  }

  return dateStr;
}

/**
 * Compare extracted vs expected
 */
function compareInvoice(extracted: IInvoice, expected: IInvoice): { match: boolean; errors: string[] } {
  const errors: string[] = [];

  const extNum = extracted.invoice_number?.replace(/\s/g, '').toLowerCase() || '';
  const expNum = expected.invoice_number?.replace(/\s/g, '').toLowerCase() || '';
  if (extNum !== expNum) {
    errors.push(`invoice_number: expected "${expected.invoice_number}", got "${extracted.invoice_number}"`);
  }

  if (normalizeDate(extracted.invoice_date) !== normalizeDate(expected.invoice_date)) {
    errors.push(`invoice_date: expected "${expected.invoice_date}", got "${extracted.invoice_date}"`);
  }

  if (Math.abs(extracted.total_amount - expected.total_amount) > 0.02) {
    errors.push(`total_amount: expected ${expected.total_amount}, got ${extracted.total_amount}`);
  }

  if (extracted.currency?.toUpperCase() !== expected.currency?.toUpperCase()) {
    errors.push(`currency: expected "${expected.currency}", got "${extracted.currency}"`);
  }

  return { match: errors.length === 0, errors };
}

/**
 * Find test cases
 */
function findTestCases(): Array<{ name: string; pdfPath: string; jsonPath: string }> {
  const testDir = path.join(process.cwd(), '.nogit/invoices');
  if (!fs.existsSync(testDir)) return [];

  const files = fs.readdirSync(testDir);
  const testCases: Array<{ name: string; pdfPath: string; jsonPath: string }> = [];

  for (const pdf of files.filter((f) => f.endsWith('.pdf'))) {
    const baseName = pdf.replace('.pdf', '');
    const jsonFile = `${baseName}.json`;
    if (files.includes(jsonFile)) {
      testCases.push({
        name: baseName,
        pdfPath: path.join(testDir, pdf),
        jsonPath: path.join(testDir, jsonFile),
      });
    }
  }

  return testCases.sort((a, b) => a.name.localeCompare(b.name));
}

/**
 * Ensure Qwen3-VL 8B model is available
 */
async function ensureQwen3Vl(): Promise<boolean> {
  try {
    const response = await fetch(`${OLLAMA_URL}/api/tags`);
    if (response.ok) {
      const data = await response.json();
      const models = data.models || [];
      if (models.some((m: { name: string }) => m.name === VISION_MODEL)) {
        console.log(`[Ollama] Model already available: ${VISION_MODEL}`);
        return true;
      }
    }
  } catch {
    console.log('[Ollama] Cannot check models');
    return false;
  }

  console.log(`[Ollama] Pulling model: ${VISION_MODEL}...`);
  const pullResponse = await fetch(`${OLLAMA_URL}/api/pull`, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ name: VISION_MODEL, stream: false }),
  });

  return pullResponse.ok;
}

// Tests

tap.test('setup: ensure Qwen3-VL is running', async () => {
  console.log('\n[Setup] Checking Qwen3-VL 8B...\n');

  // Ensure Ollama service is running
  const ollamaOk = await ensureMiniCpm();
  expect(ollamaOk).toBeTrue();

  // Ensure Qwen3-VL 8B model
  const visionOk = await ensureQwen3Vl();
  expect(visionOk).toBeTrue();

  console.log('\n[Setup] Ready!\n');
});

const testCases = findTestCases();
console.log(`\nFound ${testCases.length} invoice test cases (Qwen3-VL Vision)\n`);

let passedCount = 0;
let failedCount = 0;
const times: number[] = [];

for (const testCase of testCases) {
  tap.test(`should extract invoice: ${testCase.name}`, async () => {
    const expected: IInvoice = JSON.parse(fs.readFileSync(testCase.jsonPath, 'utf-8'));
    console.log(`\n=== ${testCase.name} ===`);
    console.log(`Expected: ${expected.invoice_number} | ${expected.invoice_date} | ${expected.total_amount} ${expected.currency}`);

    const start = Date.now();
    const images = convertPdfToImages(testCase.pdfPath);
    console.log(`  Pages: ${images.length}`);

    const extracted = await extractInvoiceFromImages(images);
    console.log(`  Extracted: ${extracted.invoice_number} | ${extracted.invoice_date} | ${extracted.total_amount} ${extracted.currency}`);
    const elapsed = Date.now() - start;
    times.push(elapsed);

    const result = compareInvoice(extracted, expected);

    if (result.match) {
      passedCount++;
      console.log(`  Result: MATCH (${(elapsed / 1000).toFixed(1)}s)`);
    } else {
      failedCount++;
      console.log(`  Result: MISMATCH (${(elapsed / 1000).toFixed(1)}s)`);
      result.errors.forEach((e) => console.log(`    - ${e}`));
    }

    expect(result.match).toBeTrue();
  });
}

tap.test('summary', async () => {
  const total = testCases.length;
  const accuracy = total > 0 ? (passedCount / total) * 100 : 0;
  const totalTime = times.reduce((a, b) => a + b, 0) / 1000;
  const avgTime = times.length > 0 ? totalTime / times.length : 0;

  console.log(`\n======================================================`);
  console.log(`   Invoice Extraction Summary (Qwen3-VL Vision)`);
  console.log(`======================================================`);
  console.log(`  Method:    Multi-query (single pass)`);
  console.log(`  Passed:    ${passedCount}/${total}`);
  console.log(`  Failed:    ${failedCount}/${total}`);
  console.log(`  Accuracy:  ${accuracy.toFixed(1)}%`);
  console.log(`------------------------------------------------------`);
  console.log(`  Total time:   ${totalTime.toFixed(1)}s`);
  console.log(`  Avg per inv:  ${avgTime.toFixed(1)}s`);
  console.log(`======================================================\n`);
});

export default tap.start();