fil/docs/snippets/php/config/pdf_config.md

<?php

declare(strict_types=1);

require_once __DIR__ . '/vendor/autoload.php';

use function Kreuzberg\extract_file;
use Kreuzberg\Config\ExtractionConfig;
use Kreuzberg\Config\PdfConfig;

/**
 * PDF configuration with hierarchy detection
 */
$config = new ExtractionConfig(
    pdf: new PdfConfig(
        extractImages: true,
        extractMetadata: true,
        passwords: ['password1', 'password2'],
        hierarchy: [
            'enabled' => true,
            'k_clusters' => 6,
            'include_bbox' => true,
            'ocr_coverage_threshold' => 0.5
        ]
    )
);

$result = extract_file('document.pdf', config: $config);

echo "Content length: " . strlen($result->content) . " characters\n";
echo "Metadata: " . implode(', ', array_keys((array) $result->metadata)) . "\n";