Nomad changes

docs/snippets/dart/config/advanced_config.md

@@ -0,0 +1,64 @@
+```dart title="Dart"
+import 'package:flutter_rust_bridge/flutter_rust_bridge.dart' show Int64List;
+
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    ocr: const OcrConfig(
+      enabled: true,
+      backend: 'tesseract',
+      language: 'eng',
+      autoRotate: false,
+    ),
+    chunking: const ChunkingConfig(
+      maxCharacters: 1000,
+      overlap: 200,
+      trim: true,
+      chunkerType: ChunkerType.text,
+      sizing: ChunkSizing.characters(),
+      prependHeadingContext: false,
+      embedding: EmbeddingConfig(
+        model: EmbeddingModelType.preset(name: 'balanced'),
+        normalize: true,
+        batchSize: 32,
+        showDownloadProgress: false,
+      ),
+    ),
+    languageDetection: const LanguageDetectionConfig(
+      enabled: true,
+      minConfidence: 0.8,
+      detectMultiple: false,
+    ),
+    keywords: KeywordConfig(
+      algorithm: KeywordAlgorithm.yake,
+      maxKeywords: 10,
+      minScore: 0.1,
+      ngramRange: Int64List.fromList(<int>[1, 3]),
+      language: 'en',
+    ),
+    tokenReduction: const TokenReductionOptions(
+      mode: 'moderate',
+      preserveImportantWords: true,
+    ),
+    postprocessor: const PostProcessorConfig(enabled: true),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    useLayoutForMarkdown: false,
+    maxArchiveDepth: 3,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Content: ${result.content}');
+  if (result.detectedLanguages != null) {
+    print('Languages: ${result.detectedLanguages}');
+  }
+  final chunks = result.chunks ?? const [];
+  print('Chunks: ${chunks.length}');
+}
+```

docs/snippets/dart/config/chunking_config.md

@@ -0,0 +1,32 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    chunking: const ChunkingConfig(
+      maxCharacters: 1000,
+      overlap: 200,
+      trim: true,
+      chunkerType: ChunkerType.text,
+      sizing: ChunkSizing.characters(),
+      prependHeadingContext: false,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  final chunks = result.chunks ?? const [];
+  print('Chunks: ${chunks.length}');
+  for (final chunk in chunks) {
+    print('Length: ${chunk.content.length}');
+  }
+}
+```

docs/snippets/dart/config/config_basic.md

@@ -0,0 +1,20 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print(result.content);
+}
+```

docs/snippets/dart/config/config_discover.md

@@ -0,0 +1,22 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  // Dart bindings do not expose config-file discovery. Build a default
+  // ExtractionConfig in code and pass it explicitly to KreuzbergBridge.extractFile.
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print(result.content);
+}
+```

docs/snippets/dart/config/config_ocr.md

@@ -0,0 +1,27 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    ocr: const OcrConfig(
+      enabled: true,
+      backend: 'tesseract',
+      language: 'eng',
+      autoRotate: false,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('scanned.pdf', null, config);
+  print('Content length: ${result.content.length}');
+  print('Tables detected: ${result.tables.length}');
+}
+```

docs/snippets/dart/config/config_programmatic.md

@@ -0,0 +1,56 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    ocr: const OcrConfig(
+      enabled: true,
+      backend: 'tesseract',
+      language: 'eng+deu',
+      autoRotate: false,
+      tesseractConfig: TesseractConfig(
+        language: 'eng+deu',
+        psm: 6,
+        outputFormat: 'text',
+        oem: 3,
+        minConfidence: 0.0,
+        enableTableDetection: false,
+        tableMinConfidence: 0.5,
+        tableColumnThreshold: 20,
+        tableRowThresholdRatio: 0.5,
+        useCache: true,
+        classifyUsePreAdaptedTemplates: false,
+        languageModelNgramOn: false,
+        tesseditDontBlkrejGoodWds: false,
+        tesseditDontRowrejGoodWds: false,
+        tesseditEnableDictCorrection: false,
+        tesseditCharWhitelist: '',
+        tesseditCharBlacklist: '',
+        tesseditUsePrimaryParamsModel: false,
+        textordSpaceSizeIsVariable: false,
+        thresholdingMethod: false,
+      ),
+    ),
+    chunking: const ChunkingConfig(
+      maxCharacters: 1000,
+      overlap: 200,
+      trim: true,
+      chunkerType: ChunkerType.text,
+      sizing: ChunkSizing.characters(),
+      prependHeadingContext: false,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Content length: ${result.content.length}');
+}
+```

docs/snippets/dart/config/document_structure_config.md

@@ -0,0 +1,23 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: true,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  final document = result.document;
+  if (document != null) {
+    print('Document nodes: ${document.nodes.length}');
+  }
+}
+```

docs/snippets/dart/config/element_based_output.md

@@ -0,0 +1,29 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    resultFormat: ResultFormat.elementBased,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  final elements = result.elements ?? const [];
+  for (final element in elements) {
+    print('Type: ${element.elementType}');
+    final preview = element.text.substring(
+      0,
+      element.text.length < 100 ? element.text.length : 100,
+    );
+    print('Text: $preview');
+    print('---');
+  }
+}
+```

docs/snippets/dart/config/embedding_config.md

@@ -0,0 +1,35 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    chunking: const ChunkingConfig(
+      maxCharacters: 1000,
+      overlap: 200,
+      trim: true,
+      chunkerType: ChunkerType.text,
+      sizing: ChunkSizing.characters(),
+      prependHeadingContext: false,
+      embedding: EmbeddingConfig(
+        model: EmbeddingModelType.preset(name: 'balanced'),
+        normalize: true,
+        batchSize: 16,
+        showDownloadProgress: true,
+      ),
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  final chunks = result.chunks ?? const [];
+  print('Chunks with embeddings: ${chunks.length}');
+}
+```

docs/snippets/dart/config/html_output.md

@@ -0,0 +1,25 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    htmlOutput: const HtmlOutputConfig(
+      theme: HtmlTheme.gitHub,
+      classPrefix: 'kb-',
+      embedCss: true,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.html(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print(result.content);
+}
+```

docs/snippets/dart/config/keyword_extraction_config.md

@@ -0,0 +1,29 @@
+```dart title="Dart"
+import 'package:flutter_rust_bridge/flutter_rust_bridge.dart' show Int64List;
+
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    keywords: KeywordConfig(
+      algorithm: KeywordAlgorithm.yake,
+      maxKeywords: 10,
+      minScore: 0.1,
+      ngramRange: Int64List.fromList(<int>[1, 3]),
+      language: 'en',
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    useLayoutForMarkdown: false,
+    maxArchiveDepth: 3,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Keywords: ${result.extractedKeywords}');
+}
+```

docs/snippets/dart/config/language_detection_config.md

@@ -0,0 +1,25 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    languageDetection: const LanguageDetectionConfig(
+      enabled: true,
+      minConfidence: 0.8,
+      detectMultiple: true,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Detected languages: ${result.detectedLanguages}');
+}
+```

docs/snippets/dart/config/ocr_dpi_config.md

@@ -0,0 +1,31 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    images: const ImageExtractionConfig(
+      extractImages: true,
+      targetDpi: 300,
+      maxImageDimension: 4096,
+      injectPlaceholders: false,
+      autoAdjustDpi: true,
+      minDpi: 150,
+      maxDpi: 600,
+      classify: false,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  final images = result.images ?? const [];
+  print('Extracted images: ${images.length}');
+}
+```

docs/snippets/dart/config/pdf_config.md

@@ -0,0 +1,32 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    pdfOptions: const PdfConfig(
+      extractImages: true,
+      passwords: <String>['password123'],
+      extractMetadata: true,
+      extractAnnotations: false,
+      allowSingleColumnTables: false,
+      hierarchy: HierarchyConfig(
+        enabled: true,
+        kClusters: 4,
+        includeBbox: false,
+      ),
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('encrypted.pdf', null, config);
+  print('Title: ${result.metadata.title}');
+}
+```

docs/snippets/dart/config/pdf_hierarchy_config.md

@@ -0,0 +1,33 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    pdfOptions: const PdfConfig(
+      extractImages: false,
+      extractMetadata: true,
+      extractAnnotations: false,
+      allowSingleColumnTables: false,
+      hierarchy: HierarchyConfig(
+        enabled: true,
+        kClusters: 5,
+        includeBbox: true,
+        ocrCoverageThreshold: 0.8,
+      ),
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  final pages = result.pages ?? const [];
+  print('Pages with hierarchy: ${pages.where((p) => p.hierarchy != null).length}');
+}
+```

docs/snippets/dart/config/postprocessor_config.md

@@ -0,0 +1,27 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    postprocessor: const PostProcessorConfig(
+      enabled: true,
+      enabledProcessors: <String>[
+        'whitespace_normalizer',
+        'unicode_normalizer',
+      ],
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Processed content: ${result.content}');
+}
+```

docs/snippets/dart/config/quality_processing_config.md

@@ -0,0 +1,21 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Quality score: ${result.qualityScore}');
+  print('Warnings: ${result.processingWarnings.length}');
+}
+```

docs/snippets/dart/config/tesseract_config.md

@@ -0,0 +1,48 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    ocr: const OcrConfig(
+      enabled: true,
+      backend: 'tesseract',
+      language: 'eng+deu',
+      autoRotate: false,
+      tesseractConfig: TesseractConfig(
+        language: 'eng+deu',
+        psm: 6,
+        outputFormat: 'text',
+        oem: 3,
+        minConfidence: 0.0,
+        enableTableDetection: false,
+        tableMinConfidence: 0.5,
+        tableColumnThreshold: 20,
+        tableRowThresholdRatio: 0.5,
+        useCache: true,
+        classifyUsePreAdaptedTemplates: false,
+        languageModelNgramOn: false,
+        tesseditDontBlkrejGoodWds: false,
+        tesseditDontRowrejGoodWds: false,
+        tesseditEnableDictCorrection: false,
+        tesseditCharWhitelist: '',
+        tesseditCharBlacklist: '',
+        tesseditUsePrimaryParamsModel: false,
+        textordSpaceSizeIsVariable: false,
+        thresholdingMethod: false,
+      ),
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('scanned.pdf', null, config);
+  print('OCR text: ${result.content}');
+}
+```

docs/snippets/dart/config/token_reduction_config.md

@@ -0,0 +1,24 @@
+```dart title="Dart"
+import 'package:kreuzberg/kreuzberg.dart';
+
+Future<void> main() async {
+  final config = ExtractionConfig(
+    useCache: true,
+    enableQualityProcessing: true,
+    forceOcr: false,
+    disableOcr: false,
+    tokenReduction: const TokenReductionOptions(
+      mode: 'moderate',
+      preserveImportantWords: true,
+    ),
+    resultFormat: ResultFormat.unified,
+    outputFormat: OutputFormat.plain(),
+    includeDocumentStructure: false,
+    maxArchiveDepth: 3,
+    useLayoutForMarkdown: false,
+  );
+
+  final result = await KreuzbergBridge.extractFile('document.pdf', null, config);
+  print('Reduced content: ${result.content}');
+}
+```