Files
fil/docs/snippets/php/config/chunking_config.md
Henrik Jess Nielsen b4c07d3693
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Nomad changes
2026-06-01 23:40:55 +02:00

1.4 KiB

<?php
declare(strict_types=1);

use Kreuzberg\Kreuzberg;
use Kreuzberg\ExtractionConfig;
use Kreuzberg\ChunkingConfig;

// Basic chunking
$config = new ExtractionConfig(
    chunking: new ChunkingConfig(
        maxCharacters: 1000,
        overlap: 200
    )
);

$result = Kreuzberg::extractFileSync('document.pdf', null, $config);

echo "Number of chunks: " . count($result->getChunks()) . "\n";
foreach ($result->getChunks() as $chunk) {
    echo "Chunk size: " . strlen($chunk->getContent()) . " characters\n";
}
?>
<?php
declare(strict_types=1);

use Kreuzberg\Kreuzberg;
use Kreuzberg\ExtractionConfig;
use Kreuzberg\ChunkingConfig;

$config = new ExtractionConfig(
    chunking: new ChunkingConfig(
        maxCharacters: 500,
        overlap: 50,
        chunkerType: 'markdown',
        prependHeadingContext: true
    )
);

$result = Kreuzberg::extractFileSync('document.md', null, $config);

foreach ($result->getChunks() as $chunk) {
    $metadata = $chunk->getMetadata();
    if ($metadata && $metadata->getHeadingContext()) {
        $headings = $metadata->getHeadingContext()->getHeadings();
        foreach ($headings as $heading) {
            echo "Heading L" . $heading->getLevel() . ": " . $heading->getText() . "\n";
        }
    }
    echo "Content: " . substr($chunk->getContent(), 0, 100) . "...\n";
}
?>