Nomad changes

docs/snippets/php/config/advanced_config.md

@@ -0,0 +1,47 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\OcrConfig;
+use Kreuzberg\ChunkingConfig;
+use Kreuzberg\LanguageDetectionConfig;
+use Kreuzberg\TokenReductionOptions;
+use Kreuzberg\PostProcessorConfig;
+use Kreuzberg\EmbeddingConfig;
+
+// Advanced configuration combining multiple features
+$config = new ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    ocr: new OcrConfig(
+        backend: 'tesseract',
+        language: 'eng'
+    ),
+    chunking: new ChunkingConfig(
+        maxCharacters: 1000,
+        overlap: 200
+    ),
+    languageDetection: new LanguageDetectionConfig(
+        enabled: true,
+        minConfidence: 0.8,
+        detectMultiple: false
+    ),
+    tokenReduction: new TokenReductionOptions(
+        mode: 'moderate',
+        preserveImportantWords: true
+    ),
+    postprocessor: new PostProcessorConfig(
+        enabled: true
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Content length: " . strlen($result->getContent()) . " characters\n";
+if ($result->getDetectedLanguages()) {
+    echo "Languages: " . implode(', ', $result->getDetectedLanguages()) . "\n";
+}
+?>
+```

docs/snippets/php/config/chunking_config.md

@@ -0,0 +1,56 @@
+```php title="PHP"
+<?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 title="PHP - Markdown with Heading Context"
+<?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";
+}
+?>
+```

docs/snippets/php/config/config_basic.md

@@ -0,0 +1,17 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+
+$config = new ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo $result->getContent();
+?>
+```

docs/snippets/php/config/config_discover.md

@@ -0,0 +1,13 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+
+// Discover configuration from file system
+$config = ExtractionConfig::discover() ?? new ExtractionConfig();
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo $result->getContent();
+?>
+```

docs/snippets/php/config/config_ocr.md

@@ -0,0 +1,21 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\OcrConfig;
+
+$config = new ExtractionConfig(
+    ocr: new OcrConfig(
+        backend: 'tesseract',
+        language: 'eng'
+    )
+);
+
+$result = Kreuzberg::extractFileSync('scanned.pdf', null, $config);
+
+echo "Content length: " . strlen($result->getContent()) . " characters\n";
+echo "Tables detected: " . count($result->getTables()) . "\n";
+?>
+```

docs/snippets/php/config/config_programmatic.md

@@ -0,0 +1,29 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\OcrConfig;
+use Kreuzberg\ChunkingConfig;
+use Kreuzberg\TesseractConfig;
+
+$config = new ExtractionConfig(
+    useCache: true,
+    ocr: new OcrConfig(
+        backend: 'tesseract',
+        language: 'eng+deu',
+        tesseractConfig: new TesseractConfig(psm: 6)
+    ),
+    chunking: new ChunkingConfig(
+        maxCharacters: 1000,
+        overlap: 200
+    ),
+    enableQualityProcessing: true
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Content length: " . strlen($result->getContent()) . " characters\n";
+?>
+```

docs/snippets/php/config/document_structure_config.md

@@ -0,0 +1,16 @@
+```php title="Document Structure Config (PHP)"
+<?php
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\Kreuzberg;
+
+$config = new ExtractionConfig(includeDocumentStructure: true);
+
+$result = Kreuzberg::extractFileSync('document.pdf', $config);
+
+if ($result->document !== null) {
+    foreach ($result->document->nodes as $node) {
+        echo "[{$node->content->nodeType}]\n";
+    }
+}
+?>
+```

docs/snippets/php/config/element_based_output.md

@@ -0,0 +1,42 @@
+```php title="Element-Based Output (PHP)"
+<?php
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\Kreuzberg;
+
+// Configure element-based output
+$config = new ExtractionConfig();
+$config->setOutputFormat('element_based');
+
+// Extract document
+$result = Kreuzberg::extractFileSync('document.pdf', $config);
+
+// Access elements
+foreach ($result->getElements() as $element) {
+    echo "Type: " . $element->getElementType() . "\n";
+    echo "Text: " . substr($element->getText(), 0, 100) . "\n";
+
+    if ($element->getMetadata()->getPageNumber()) {
+        echo "Page: " . $element->getMetadata()->getPageNumber() . "\n";
+    }
+
+    if ($element->getMetadata()->getCoordinates()) {
+        $coords = $element->getMetadata()->getCoordinates();
+        echo sprintf("Coords: (%s, %s) - (%s, %s)\n",
+            $coords->getLeft(), $coords->getTop(),
+            $coords->getRight(), $coords->getBottom());
+    }
+
+    echo "---\n";
+}
+
+// Filter by element type
+$titles = array_filter($result->getElements(), function($e) {
+    return $e->getElementType() === 'title';
+});
+
+foreach ($titles as $title) {
+    $level = $title->getMetadata()->getAdditional()['level'] ?? 'unknown';
+    echo "[{$level}] {$title->getText()}\n";
+}
+?>
+```

docs/snippets/php/config/embedding_config.md

@@ -0,0 +1,27 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\ChunkingConfig;
+use Kreuzberg\EmbeddingConfig;
+
+$config = new ExtractionConfig(
+    chunking: new ChunkingConfig(
+        maxCharacters: 1000,
+        overlap: 200,
+        embedding: new EmbeddingConfig(
+            model: 'balanced',
+            batchSize: 16,
+            normalize: true,
+            showDownloadProgress: true
+        )
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Chunks with embeddings: " . count($result->getChunks()) . "\n";
+?>
+```

docs/snippets/php/config/html_output.md

@@ -0,0 +1,21 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\HtmlOutputConfig;
+
+$config = new ExtractionConfig(
+    resultFormat: 'html',
+    htmlOutput: new HtmlOutputConfig(
+        theme: 'github'
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+// Output HTML with kb-* CSS classes
+echo $result->getContent();
+?>
+```

docs/snippets/php/config/keyword_extraction_config.md

@@ -0,0 +1,26 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\KeywordConfig;
+
+$config = new ExtractionConfig(
+    keywords: new KeywordConfig(
+        algorithm: 'yake',
+        maxKeywords: 10,
+        minScore: 0.1,
+        language: 'en'
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+if ($result->getKeywords()) {
+    foreach ($result->getKeywords() as $keyword) {
+        echo $keyword . "\n";
+    }
+}
+?>
+```

docs/snippets/php/config/language_detection_config.md

@@ -0,0 +1,22 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\LanguageDetectionConfig;
+
+$config = new ExtractionConfig(
+    languageDetection: new LanguageDetectionConfig(
+        enabled: true,
+        minConfidence: 0.8,
+        detectMultiple: true
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Detected language: " . $result->getLanguage() . "\n";
+echo "Confidence: " . $result->getLanguageConfidence() . "\n";
+?>
+```

docs/snippets/php/config/ocr_dpi_config.md

@@ -0,0 +1,24 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\ImageExtractionConfig;
+
+$config = new ExtractionConfig(
+    images: new ImageExtractionConfig(
+        extractImages: true,
+        targetDpi: 300,
+        maxImageDimension: 4096,
+        autoAdjustDpi: true,
+        minDpi: 150,
+        maxDpi: 600
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Extracted images: " . count($result->getImages()) . "\n";
+?>
+```

docs/snippets/php/config/pdf_config.md

@@ -0,0 +1,33 @@
+```php title="PHP"
+<?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";
+```

docs/snippets/php/config/pdf_hierarchy_config.md

@@ -0,0 +1,26 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\PdfConfig;
+use Kreuzberg\HierarchyConfig;
+
+$config = new ExtractionConfig(
+    pdfOptions: new PdfConfig(
+        hierarchy: new HierarchyConfig(
+            enabled: true,
+            detectionThreshold: 0.75,
+            ocrCoverageThreshold: 0.8,
+            minLevel: 1,
+            maxLevel: 5
+        )
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Hierarchy levels: " . count($result->getHierarchy()) . "\n";
+?>
+```

docs/snippets/php/config/postprocessor_config.md

@@ -0,0 +1,23 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\PostProcessorConfig;
+
+$config = new ExtractionConfig(
+    postprocessor: new PostProcessorConfig(
+        enabled: true,
+        enabledProcessors: [
+            'whitespace_normalizer',
+            'unicode_normalizer'
+        ]
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Processed content: " . substr($result->getContent(), 0, 100) . "...\n";
+?>
+```

docs/snippets/php/config/quality_processing_config.md

@@ -0,0 +1,20 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+
+$config = new ExtractionConfig(
+    enableQualityProcessing: true,
+    useCache: true
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Quality score: " . $result->getQualityScore() . "\n";
+if ($result->getProcessingTime()) {
+    echo "Processing time: " . $result->getProcessingTime() . "ms\n";
+}
+?>
+```

docs/snippets/php/config/tesseract_config.md

@@ -0,0 +1,25 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\OcrConfig;
+use Kreuzberg\TesseractConfig;
+
+$config = new ExtractionConfig(
+    ocr: new OcrConfig(
+        backend: 'tesseract',
+        language: 'eng+deu',
+        tesseractConfig: new TesseractConfig(
+            psm: 6,
+            oem: 3
+        )
+    )
+);
+
+$result = Kreuzberg::extractFileSync('scanned.pdf', null, $config);
+
+echo "OCR text: " . substr($result->getContent(), 0, 100) . "...\n";
+?>
+```

docs/snippets/php/config/token_reduction_config.md

@@ -0,0 +1,21 @@
+```php title="PHP"
+<?php
+declare(strict_types=1);
+
+use Kreuzberg\Kreuzberg;
+use Kreuzberg\ExtractionConfig;
+use Kreuzberg\TokenReductionOptions;
+
+$config = new ExtractionConfig(
+    tokenReduction: new TokenReductionOptions(
+        mode: 'moderate',
+        preserveImportantWords: true
+    )
+);
+
+$result = Kreuzberg::extractFileSync('document.pdf', null, $config);
+
+echo "Original token count: " . $result->getTokenCount() . "\n";
+echo "Reduced content: " . substr($result->getContent(), 0, 100) . "...\n";
+?>
+```