Nomad changes

docs/snippets/ruby/advanced/chunk_page_mapping.md

@@ -0,0 +1,18 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  chunking: Kreuzberg::ChunkingConfig.new(max_characters: 500, overlap: 50),
+)
+
+result = Kreuzberg.extract_file_sync('document.pdf', config: config)
+
+result.chunks&.each do |chunk|
+  first = chunk.metadata.first_page
+  last = chunk.metadata.last_page
+  next if first.nil?
+
+  page_range = first == last ? "Page #{first}" : "Pages #{first}-#{last}"
+  puts "Chunk: #{chunk.content[0..50]}... (#{page_range})"
+end
+```

docs/snippets/ruby/advanced/chunking_config.md

@@ -0,0 +1,31 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  chunking: Kreuzberg::ChunkingConfig.new(
+    max_characters: 1000,
+    overlap: 200,
+    embedding: Kreuzberg::EmbeddingConfig.new(
+      model: Kreuzberg::EmbeddingModelType.new(
+        type: 'preset',
+        name: 'all-minilm-l6-v2'
+      ),
+      normalize: true,
+      batch_size: 32
+    )
+  )
+)
+```
+
+```ruby title="Ruby - Prepend Heading Context"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  chunking: Kreuzberg::ChunkingConfig.new(
+    chunker_type: "markdown",
+    max_characters: 500,
+    overlap: 50,
+    prepend_heading_context: true
+  )
+)
+```

docs/snippets/ruby/advanced/chunking_rag.md

@@ -0,0 +1,45 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  chunking: Kreuzberg::ChunkingConfig.new(
+    max_characters: 500,
+    overlap: 50,
+    embedding: Kreuzberg::EmbeddingConfig.new(
+      model: Kreuzberg::EmbeddingModelType.new(
+        type: 'preset',
+        name: 'all-mpnet-base-v2'
+      ),
+      normalize: true,
+      batch_size: 16
+    )
+  )
+)
+
+result = Kreuzberg.extract_file_sync('research_paper.pdf', config: config)
+
+vector_store = build_vector_store(result.chunks)
+query = 'machine learning optimization'
+relevant_chunks = search_vector_store(vector_store, query)
+
+puts "Found #{relevant_chunks.length} relevant chunks"
+relevant_chunks.take(3).each do |chunk|
+  puts "Content: #{chunk[:content][0..80]}..."
+  puts "Similarity: #{chunk[:similarity]&.round(3)}\n"
+end
+
+def build_vector_store(chunks)
+  chunks.map.with_index do |chunk, idx|
+    {
+      id: idx,
+      content: chunk.content,
+      embedding: chunk.embedding,
+      similarity: 0.0
+    }
+  end
+end
+
+def search_vector_store(store, query)
+  store.sort_by { |entry| entry[:similarity] }.reverse
+end
+```

docs/snippets/ruby/advanced/embedding_with_chunking.md

@@ -0,0 +1,31 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  chunking: Kreuzberg::ChunkingConfig.new(
+    max_characters: 512,
+    overlap: 50,
+    embedding: Kreuzberg::EmbeddingConfig.new(
+      model: Kreuzberg::EmbeddingModelType.new(
+        type: 'preset',
+        name: 'balanced'
+      ),
+      normalize: true,
+      batch_size: 32,
+      show_download_progress: false
+    )
+  )
+)
+
+result = Kreuzberg.extract_file_sync('document.pdf', config: config)
+
+chunks = result.chunks || []
+chunks.each_with_index do |chunk, idx|
+  chunk_id = "doc_chunk_#{idx}"
+  puts "Chunk #{chunk_id}: #{chunk.content[0...50]}"
+
+  if chunk.embedding
+    puts "  Embedding dimensions: #{chunk.embedding.length}"
+  end
+end
+```

docs/snippets/ruby/advanced/keyword_extraction_config.md

@@ -0,0 +1,13 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  keywords: Kreuzberg::KeywordConfig.new(
+    algorithm: Kreuzberg::KeywordAlgorithm::YAKE,
+    max_keywords: 10,
+    min_score: 0.3,
+    ngram_range: [1, 3],
+    language: 'en'
+  )
+)
+```

docs/snippets/ruby/advanced/keyword_extraction_example.md

@@ -0,0 +1,20 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  keywords: Kreuzberg::KeywordConfig.new(
+    algorithm: Kreuzberg::KeywordAlgorithm::YAKE,
+    max_keywords: 10,
+    min_score: 0.3
+  )
+)
+
+result = Kreuzberg.extract_file_sync('research_paper.pdf', config: config)
+
+keywords = result.metadata&.dig('keywords') || []
+keywords.each do |kw|
+  text = kw['text']
+  score = kw['score']
+  puts "#{text}: #{score.round(3)}"
+end
+```

docs/snippets/ruby/advanced/language_detection_config.md

@@ -0,0 +1,21 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  language_detection: Kreuzberg::LanguageDetectionConfig.new(
+    enabled: true,
+    min_confidence: 0.8,
+    detect_multiple: false
+  )
+)
+
+result = Kreuzberg.extract_file_sync('document.pdf', config: config)
+
+if result.detected_languages&.any?
+  puts "Detected Language: #{result.detected_languages.first}"
+else
+  puts "No language detected"
+end
+
+puts "Content length: #{result.content.length} characters"
+```

docs/snippets/ruby/advanced/language_detection_multilingual.md

@@ -0,0 +1,24 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  language_detection: Kreuzberg::LanguageDetectionConfig.new(
+    enabled: true,
+    min_confidence: 0.8,
+    detect_multiple: true
+  )
+)
+
+result = Kreuzberg.extract_file_sync('multilingual_document.pdf', config: config)
+
+languages = result.detected_languages || []
+
+if languages.any?
+  puts "Detected #{languages.length} language(s): #{languages.join(', ')}"
+else
+  puts "No languages detected"
+end
+
+puts "Total content: #{result.content.length} characters"
+puts "MIME type: #{result.mime_type}"
+```

docs/snippets/ruby/advanced/quality_processing_config.md

@@ -0,0 +1,7 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  enable_quality_processing: true
+)
+```

docs/snippets/ruby/advanced/quality_processing_example.md

@@ -0,0 +1,18 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  enable_quality_processing: true
+)
+
+result = Kreuzberg.extract_file_sync('scanned_document.pdf', config: config)
+
+quality_score = result.quality_score || 0.0
+
+if quality_score < 0.5
+  puts "Warning: Low quality extraction (#{quality_score.round(2)})"
+  puts "Consider re-scanning with higher DPI or adjusting OCR settings"
+else
+  puts "Quality score: #{quality_score.round(2)}"
+end
+```

docs/snippets/ruby/advanced/token_reduction_config.md

@@ -0,0 +1,12 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  token_reduction: Kreuzberg::TokenReductionConfig.new(
+    mode: 'moderate',
+    preserve_markdown: true,
+    preserve_code: true,
+    language_hint: 'eng'
+  )
+)
+```

docs/snippets/ruby/advanced/token_reduction_example.md

@@ -0,0 +1,19 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  token_reduction: Kreuzberg::TokenReductionConfig.new(
+    mode: 'moderate',
+    preserve_markdown: true
+  )
+)
+
+result = Kreuzberg.extract_file_sync('verbose_document.pdf', config: config)
+
+original_tokens = result.metadata&.dig('original_token_count') || 0
+reduced_tokens = result.metadata&.dig('token_count') || 0
+reduction_ratio = result.metadata&.dig('token_reduction_ratio') || 0.0
+
+puts "Reduced from #{original_tokens} to #{reduced_tokens} tokens"
+puts "Reduction: #{(reduction_ratio * 100).round(1)}%"
+```

docs/snippets/ruby/advanced/vector_database_integration.md

@@ -0,0 +1,53 @@
+```ruby title="Ruby"
+require 'kreuzberg'
+
+class VectorDatabaseIntegration
+  VectorRecord = Struct.new(:id, :embedding, :content, :metadata, keyword_init: true)
+
+  def extract_and_vectorize(document_path, document_id)
+    config = Kreuzberg::ExtractionConfig.new(
+      chunking: Kreuzberg::ChunkingConfig.new(
+        max_characters: 512,
+        overlap: 50,
+        embedding: Kreuzberg::EmbeddingConfig.new(
+          model: Kreuzberg::EmbeddingModelType.new(
+            type: 'preset',
+            name: 'balanced'
+          ),
+          normalize: true,
+          batch_size: 32
+        )
+      )
+    )
+
+    result = Kreuzberg.extract_file_sync(document_path, config: config)
+    chunks = result.chunks || []
+
+    vector_records = chunks.map.with_index do |chunk, idx|
+      VectorRecord.new(
+        id: "#{document_id}_chunk_#{idx}",
+        content: chunk.content,
+        embedding: chunk.embedding,
+        metadata: {
+          document_id: document_id,
+          chunk_index: idx,
+          content_length: chunk.content.length
+        }
+      )
+    end
+
+    store_in_vector_database(vector_records)
+    vector_records
+  end
+
+  private
+
+  def store_in_vector_database(records)
+    records.each do |record|
+      if record.embedding&.any?
+        puts "Storing #{record.id}: #{record.content.length} chars, #{record.embedding.length} dims"
+      end
+    end
+  end
+end
+```