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

/**
 * Invoice extraction using Nanonets-OCR-s + GPT-OSS 20B (sequential two-stage pipeline)
 *
 * Stage 1: Nanonets-OCR-s converts ALL document pages to markdown (stop after completion)
 * Stage 2: GPT-OSS 20B extracts structured JSON from saved markdown (after Nanonets stops)
 *
 * This approach avoids GPU contention by running services sequentially.
 */
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 { ensureNanonetsOcr, ensureMiniCpm, isContainerRunning } from './helpers/docker.js';

const NANONETS_URL = 'http://localhost:8000/v1';
const NANONETS_MODEL = 'nanonets/Nanonets-OCR-s';

const OLLAMA_URL = 'http://localhost:11434';
const EXTRACTION_MODEL = 'gpt-oss:20b';

// Temp directory for storing markdown between stages
const TEMP_MD_DIR = path.join(os.tmpdir(), 'nanonets-invoices-markdown');

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

interface IImageData {
  base64: string;
  width: number;
  height: number;
  pageNum: number;
}

interface ITestCase {
  name: string;
  pdfPath: string;
  jsonPath: string;
  markdownPath?: string;
}

// Nanonets-specific prompt for document OCR to markdown
const NANONETS_OCR_PROMPT = `Extract the text from the above document as if you were reading it naturally.
Return the tables in html format.
Return the equations in LaTeX representation.
If there is an image in the document and image caption is not present, add a small description inside <img></img> tag.
Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>.
Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number>.`;

// JSON extraction prompt for GPT-OSS 20B
const JSON_EXTRACTION_PROMPT = `You are an invoice data extractor. Below is an invoice document converted to text/markdown. Extract the key invoice fields as JSON.

IMPORTANT RULES:
1. invoice_number: The unique invoice/document number (NOT VAT ID, NOT customer ID)
2. invoice_date: Format as YYYY-MM-DD
3. vendor_name: The company that issued the invoice
4. currency: EUR, USD, or GBP
5. net_amount: Amount before tax
6. vat_amount: Tax/VAT amount
7. total_amount: Final total (gross amount)

Return ONLY this JSON format, no explanation:
{
  "invoice_number": "INV-2024-001",
  "invoice_date": "2024-01-15",
  "vendor_name": "Company Name",
  "currency": "EUR",
  "net_amount": 100.00,
  "vat_amount": 19.00,
  "total_amount": 119.00
}

INVOICE TEXT:
`;

// Constants for smart batching
const MAX_VISUAL_TOKENS = 28000;  // ~32K context minus prompt/output headroom
const PATCH_SIZE = 14;  // Qwen2.5-VL uses 14x14 patches

/**
 * Estimate visual tokens for an image based on dimensions
 */
function estimateVisualTokens(width: number, height: number): number {
  return Math.ceil((width * height) / (PATCH_SIZE * PATCH_SIZE));
}

/**
 * Batch images to fit within context window
 */
function batchImages(images: IImageData[]): IImageData[][] {
  const batches: IImageData[][] = [];
  let currentBatch: IImageData[] = [];
  let currentTokens = 0;

  for (const img of images) {
    const imgTokens = estimateVisualTokens(img.width, img.height);

    if (currentTokens + imgTokens > MAX_VISUAL_TOKENS && currentBatch.length > 0) {
      batches.push(currentBatch);
      currentBatch = [img];
      currentTokens = imgTokens;
    } else {
      currentBatch.push(img);
      currentTokens += imgTokens;
    }
  }
  if (currentBatch.length > 0) batches.push(currentBatch);

  return batches;
}

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

  try {
    execSync(
      `convert -density 150 -quality 90 "${pdfPath}" -background white -alpha remove "${outputPattern}"`,
      { stdio: 'pipe' }
    );

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

    for (let i = 0; i < files.length; i++) {
      const file = files[i];
      const imagePath = path.join(tempDir, file);
      const imageData = fs.readFileSync(imagePath);

      // Get image dimensions using identify command
      const dimensions = execSync(`identify -format "%w %h" "${imagePath}"`, { encoding: 'utf-8' }).trim();
      const [width, height] = dimensions.split(' ').map(Number);

      images.push({
        base64: imageData.toString('base64'),
        width,
        height,
        pageNum: i + 1,
      });
    }

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

/**
 * Convert a batch of pages to markdown using Nanonets-OCR-s
 */
async function convertBatchToMarkdown(batch: IImageData[]): Promise<string> {
  const startTime = Date.now();
  const pageNums = batch.map(img => img.pageNum).join(', ');

  // Build content array with all images first, then the prompt
  const content: Array<{ type: string; image_url?: { url: string }; text?: string }> = [];

  for (const img of batch) {
    content.push({
      type: 'image_url',
      image_url: { url: `data:image/jpeg;base64,${img.base64}` },
    });
  }

  // Add prompt with page separator instruction if multiple pages
  const promptText = batch.length > 1
    ? `${NANONETS_OCR_PROMPT}\n\nPlease clearly separate each page's content with "--- PAGE N ---" markers, where N is the page number starting from ${batch[0].pageNum}.`
    : NANONETS_OCR_PROMPT;

  content.push({ type: 'text', text: promptText });

  const response = await fetch(`${NANONETS_URL}/chat/completions`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer dummy',
    },
    body: JSON.stringify({
      model: NANONETS_MODEL,
      messages: [{
        role: 'user',
        content,
      }],
      max_tokens: 4096 * batch.length,  // Scale output tokens with batch size
      temperature: 0.0,
    }),
  });

  const elapsed = ((Date.now() - startTime) / 1000).toFixed(1);

  if (!response.ok) {
    const errorText = await response.text();
    throw new Error(`Nanonets API error: ${response.status} - ${errorText}`);
  }

  const data = await response.json();
  let responseContent = (data.choices?.[0]?.message?.content || '').trim();

  // For single-page batches, add page marker if not present
  if (batch.length === 1 && !responseContent.includes('--- PAGE')) {
    responseContent = `--- PAGE ${batch[0].pageNum} ---\n${responseContent}`;
  }

  console.log(`        Pages [${pageNums}]: ${responseContent.length} chars (${elapsed}s)`);
  return responseContent;
}

/**
 * Convert all pages of a document to markdown using smart batching
 */
async function convertDocumentToMarkdown(images: IImageData[], docName: string): Promise<string> {
  const batches = batchImages(images);
  console.log(`      [${docName}] Processing ${images.length} page(s) in ${batches.length} batch(es)...`);

  const markdownParts: string[] = [];

  for (let i = 0; i < batches.length; i++) {
    const batch = batches[i];
    const batchTokens = batch.reduce((sum, img) => sum + estimateVisualTokens(img.width, img.height), 0);
    console.log(`        Batch ${i + 1}: ${batch.length} page(s), ~${batchTokens} tokens`);
    const markdown = await convertBatchToMarkdown(batch);
    markdownParts.push(markdown);
  }

  const fullMarkdown = markdownParts.join('\n\n');
  console.log(`      [${docName}] Complete: ${fullMarkdown.length} chars total`);
  return fullMarkdown;
}

/**
 * Stop Nanonets container
 */
function stopNanonets(): void {
  console.log('    [Docker] Stopping Nanonets container...');
  try {
    execSync('docker stop nanonets-test 2>/dev/null || true', { stdio: 'pipe' });
    execSync('sleep 5', { stdio: 'pipe' });
    console.log('    [Docker] Nanonets stopped');
  } catch {
    console.log('    [Docker] Nanonets was not running');
  }
}

/**
 * Ensure GPT-OSS 20B model is available
 */
async function ensureExtractionModel(): 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 === EXTRACTION_MODEL)) {
        console.log(`    [Ollama] Model available: ${EXTRACTION_MODEL}`);
        return true;
      }
    }
  } catch {
    return false;
  }

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

  return pullResponse.ok;
}

/**
 * Parse amount from string (handles European format)
 */
function parseAmount(s: string | number | undefined): number {
  if (s === undefined || s === null) return 0;
  if (typeof s === 'number') return s;
  const match = s.match(/([\d.,]+)/);
  if (!match) return 0;
  const numStr = match[1];
  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
 */
function extractInvoiceNumber(s: string | undefined): string {
  if (!s) return '';
  let clean = s.replace(/\*\*/g, '').replace(/`/g, '').trim();
  const patterns = [
    /\b([A-Z]{2,3}\d{10,})\b/i,
    /\b([A-Z]\d{8,})\b/i,
    /\b(INV[-\s]?\d{4}[-\s]?\d+)\b/i,
    /\b(\d{7,})\b/,
  ];
  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
 */
function extractDate(s: string | undefined): string {
  if (!s) return '';
  let clean = s.replace(/\*\*/g, '').replace(/`/g, '').trim();
  const isoMatch = clean.match(/(\d{4}-\d{2}-\d{2})/);
  if (isoMatch) return isoMatch[1];
  const dmyMatch = clean.match(/(\d{1,2})[\/.](\d{1,2})[\/.](\d{4})/);
  if (dmyMatch) {
    return `${dmyMatch[3]}-${dmyMatch[2].padStart(2, '0')}-${dmyMatch[1].padStart(2, '0')}`;
  }
  return clean.replace(/[^\d-]/g, '').trim();
}

/**
 * Extract currency
 */
function extractCurrency(s: string | undefined): string {
  if (!s) return 'EUR';
  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';
}

/**
 * Extract JSON from response
 */
function extractJsonFromResponse(response: string): Record<string, unknown> | null {
  let cleanResponse = response.replace(/<think>[\s\S]*?<\/think>/g, '').trim();
  const codeBlockMatch = cleanResponse.match(/```(?:json)?\s*([\s\S]*?)```/);
  const jsonStr = codeBlockMatch ? codeBlockMatch[1].trim() : cleanResponse;

  try {
    return JSON.parse(jsonStr);
  } catch {
    const jsonMatch = jsonStr.match(/\{[\s\S]*\}/);
    if (jsonMatch) {
      try {
        return JSON.parse(jsonMatch[0]);
      } catch {
        return null;
      }
    }
    return null;
  }
}

/**
 * Parse JSON response into IInvoice
 */
function parseJsonToInvoice(response: string): IInvoice | null {
  const parsed = extractJsonFromResponse(response);
  if (!parsed) return null;

  return {
    invoice_number: extractInvoiceNumber(String(parsed.invoice_number || '')),
    invoice_date: extractDate(String(parsed.invoice_date || '')),
    vendor_name: String(parsed.vendor_name || '').replace(/\*\*/g, '').replace(/`/g, '').trim(),
    currency: extractCurrency(String(parsed.currency || '')),
    net_amount: parseAmount(parsed.net_amount as string | number),
    vat_amount: parseAmount(parsed.vat_amount as string | number),
    total_amount: parseAmount(parsed.total_amount as string | number),
  };
}

/**
 * Extract invoice from markdown using GPT-OSS 20B (streaming)
 */
async function extractInvoiceFromMarkdown(markdown: string, queryId: string): Promise<IInvoice | null> {
  const startTime = Date.now();
  const fullPrompt = JSON_EXTRACTION_PROMPT + markdown;

  // Log exact prompt
  console.log(`\n      [${queryId}] ===== PROMPT =====`);
  console.log(fullPrompt);
  console.log(`      [${queryId}] ===== END PROMPT (${fullPrompt.length} chars) =====\n`);

  const response = await fetch(`${OLLAMA_URL}/api/chat`, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      model: EXTRACTION_MODEL,
      messages: [
        { role: 'user', content: 'Hi there, how are you?' },
        { role: 'assistant', content: 'Good, how can I help you today?' },
        { role: 'user', content: fullPrompt },
      ],
      stream: true,
    }),
    signal: AbortSignal.timeout(600000), // 10 minute timeout for large documents
  });

  if (!response.ok) {
    const elapsed = ((Date.now() - startTime) / 1000).toFixed(1);
    console.log(`      [${queryId}] ERROR: ${response.status} (${elapsed}s)`);
    throw new Error(`Ollama API error: ${response.status}`);
  }

  // Stream the response
  let content = '';
  let thinkingContent = '';
  let thinkingStarted = false;
  let outputStarted = false;
  const reader = response.body!.getReader();
  const decoder = new TextDecoder();

  try {
    while (true) {
      const { done, value } = await reader.read();
      if (done) break;

      const chunk = decoder.decode(value, { stream: true });

      // Each line is a JSON object
      for (const line of chunk.split('\n').filter(l => l.trim())) {
        try {
          const json = JSON.parse(line);

          // Stream thinking tokens
          const thinking = json.message?.thinking || '';
          if (thinking) {
            if (!thinkingStarted) {
              process.stdout.write(`      [${queryId}] THINKING: `);
              thinkingStarted = true;
            }
            process.stdout.write(thinking);
            thinkingContent += thinking;
          }

          // Stream content tokens
          const token = json.message?.content || '';
          if (token) {
            if (!outputStarted) {
              if (thinkingStarted) process.stdout.write('\n');
              process.stdout.write(`      [${queryId}] OUTPUT: `);
              outputStarted = true;
            }
            process.stdout.write(token);
            content += token;
          }
        } catch {
          // Ignore parse errors for partial chunks
        }
      }
    }
  } finally {
    if (thinkingStarted || outputStarted) process.stdout.write('\n');
  }

  const elapsed = ((Date.now() - startTime) / 1000).toFixed(1);
  console.log(`      [${queryId}] Done: ${thinkingContent.length} thinking chars, ${content.length} output chars (${elapsed}s)`);

  return parseJsonToInvoice(content);
}

/**
 * Extract invoice (single pass - GPT-OSS is more reliable)
 */
async function extractInvoice(markdown: string, docName: string): Promise<IInvoice> {
  console.log(`    [${docName}] Extracting...`);
  const invoice = await extractInvoiceFromMarkdown(markdown, docName);
  if (!invoice) {
    return {
      invoice_number: '',
      invoice_date: '',
      vendor_name: '',
      currency: 'EUR',
      net_amount: 0,
      vat_amount: 0,
      total_amount: 0,
    };
  }
  console.log(`    [${docName}] Extracted: ${invoice.invoice_number}`);
  return invoice;
}

/**
 * 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 invoice against 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: exp "${expected.invoice_number}", got "${extracted.invoice_number}"`);
  }

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

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

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

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

/**
 * Find all test cases
 */
function findTestCases(): ITestCase[] {
  const testDir = path.join(process.cwd(), '.nogit/invoices');
  if (!fs.existsSync(testDir)) return [];

  const files = fs.readdirSync(testDir);
  const testCases: ITestCase[] = [];

  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));
}

// ============ TESTS ============

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

// Ensure temp directory exists
if (!fs.existsSync(TEMP_MD_DIR)) {
  fs.mkdirSync(TEMP_MD_DIR, { recursive: true });
}

// -------- STAGE 1: OCR with Nanonets --------

tap.test('Stage 1: Setup Nanonets', async () => {
  console.log('\n========== STAGE 1: Nanonets OCR ==========\n');
  const ok = await ensureNanonetsOcr();
  expect(ok).toBeTrue();
});

tap.test('Stage 1: Convert all invoices to markdown', async () => {
  console.log('\n  Converting all invoice PDFs to markdown with Nanonets-OCR-s...\n');

  for (const tc of testCases) {
    console.log(`\n    === ${tc.name} ===`);

    const images = convertPdfToImages(tc.pdfPath);
    console.log(`      Pages: ${images.length}`);

    const markdown = await convertDocumentToMarkdown(images, tc.name);

    const mdPath = path.join(TEMP_MD_DIR, `${tc.name}.md`);
    fs.writeFileSync(mdPath, markdown);
    tc.markdownPath = mdPath;
    console.log(`      Saved: ${mdPath}`);
  }

  console.log('\n  Stage 1 complete: All invoices converted to markdown\n');
});

tap.test('Stage 1: Stop Nanonets', async () => {
  stopNanonets();
  await new Promise(resolve => setTimeout(resolve, 3000));
  expect(isContainerRunning('nanonets-test')).toBeFalse();
});

// -------- STAGE 2: Extraction with GPT-OSS 20B --------

tap.test('Stage 2: Setup Ollama + GPT-OSS 20B', async () => {
  console.log('\n========== STAGE 2: GPT-OSS 20B Extraction ==========\n');

  const ollamaOk = await ensureMiniCpm();
  expect(ollamaOk).toBeTrue();

  const extractionOk = await ensureExtractionModel();
  expect(extractionOk).toBeTrue();
});

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

for (const tc of testCases) {
  tap.test(`Stage 2: Extract ${tc.name}`, async () => {
    const expected: IInvoice = JSON.parse(fs.readFileSync(tc.jsonPath, 'utf-8'));
    console.log(`\n    === ${tc.name} ===`);
    console.log(`    Expected: ${expected.invoice_number} | ${expected.invoice_date} | ${expected.total_amount} ${expected.currency}`);

    const startTime = Date.now();

    const mdPath = path.join(TEMP_MD_DIR, `${tc.name}.md`);
    if (!fs.existsSync(mdPath)) {
      throw new Error(`Markdown not found: ${mdPath}. Run Stage 1 first.`);
    }
    const markdown = fs.readFileSync(mdPath, 'utf-8');
    console.log(`    Markdown: ${markdown.length} chars`);

    const extracted = await extractInvoice(markdown, tc.name);

    const elapsedMs = Date.now() - startTime;
    processingTimes.push(elapsedMs);

    console.log(`    Extracted: ${extracted.invoice_number} | ${extracted.invoice_date} | ${extracted.total_amount} ${extracted.currency}`);

    const result = compareInvoice(extracted, expected);

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

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

tap.test('Summary', async () => {
  const totalInvoices = testCases.length;
  const accuracy = totalInvoices > 0 ? (passedCount / totalInvoices) * 100 : 0;
  const totalTimeMs = processingTimes.reduce((a, b) => a + b, 0);
  const avgTimeSec = processingTimes.length > 0 ? totalTimeMs / processingTimes.length / 1000 : 0;

  console.log(`\n========================================`);
  console.log(`   Invoice Summary (Nanonets + GPT-OSS 20B)`);
  console.log(`========================================`);
  console.log(`  Stage 1:   Nanonets-OCR-s (doc -> md)`);
  console.log(`  Stage 2:   GPT-OSS 20B (md -> JSON)`);
  console.log(`  Passed:    ${passedCount}/${totalInvoices}`);
  console.log(`  Failed:    ${failedCount}/${totalInvoices}`);
  console.log(`  Accuracy:  ${accuracy.toFixed(1)}%`);
  console.log(`----------------------------------------`);
  console.log(`  Total time:   ${(totalTimeMs / 1000).toFixed(1)}s`);
  console.log(`  Avg per inv:  ${avgTimeSec.toFixed(1)}s`);
  console.log(`========================================\n`);

  // Cleanup temp files
  try {
    fs.rmSync(TEMP_MD_DIR, { recursive: true, force: true });
    console.log(`  Cleaned up temp directory: ${TEMP_MD_DIR}\n`);
  } catch {
    // Ignore
  }
});

export default tap.start();