Nomad changes

docs/snippets/java/utils/chunking.md

@@ -0,0 +1,19 @@
+```java title="Java"
+import dev.kreuzberg.ChunkingConfig;
+import dev.kreuzberg.EmbeddingConfig;
+import dev.kreuzberg.EmbeddingModelType;
+import dev.kreuzberg.ExtractionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .chunking(ChunkingConfig.builder()
+        .maxChars(1500)
+        .maxOverlap(200)
+        .embedding(EmbeddingConfig.builder()
+            .model(EmbeddingModelType.builder()
+                .type("preset")
+                .name("text-embedding-all-minilm-l6-v2")
+                .build())
+            .build())
+        .build())
+    .build();
+```

docs/snippets/java/utils/chunking_rag.md

@@ -0,0 +1,19 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.ChunkingConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .chunking(ChunkingConfig.builder()
+        .maxChars(500)
+        .maxOverlap(50)
+        .embedding("balanced")
+        .build())
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("research_paper.pdf", config);
+
+System.out.println("Content: " + result.getContent()
+    .substring(0, Math.min(100, result.getContent().length())) + "...");
+```

docs/snippets/java/utils/embedding_with_chunking.md

@@ -0,0 +1,12 @@
+```java title="Java"
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.ChunkingConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .chunking(ChunkingConfig.builder()
+        .maxChars(1024)
+        .maxOverlap(100)
+        .embedding("balanced")
+        .build())
+    .build();
+```

docs/snippets/java/utils/keyword_extraction_example.md

@@ -0,0 +1,4 @@
+```java title="Java"
+// Note: Keyword extraction is not yet available in Java bindings
+// This feature requires the 'keywords' feature flag and is planned for a future release
+```

docs/snippets/java/utils/quality_processing_example.md

@@ -0,0 +1,20 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .enableQualityProcessing(true)
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("scanned_document.pdf", config);
+
+double qualityScore = result.getQualityScore() != null ? result.getQualityScore() : 0.0;
+
+if (qualityScore < 0.5) {
+    System.out.printf("Warning: Low quality extraction (%.2f)%n", qualityScore);
+    System.out.println("Consider re-scanning or adjusting OCR settings");
+} else {
+    System.out.printf("Quality score: %.2f%n", qualityScore);
+}
+```

docs/snippets/java/utils/standalone_embed.md

@@ -0,0 +1,14 @@
+```java
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.EmbeddingConfig;
+
+// Embed with default config
+float[][] embeddings = Kreuzberg.embed(List.of("Hello world", "How are you?"), null);
+
+// Embed with specific preset
+EmbeddingConfig config = EmbeddingConfig.withPreset("fast");
+float[][] fastEmbeddings = Kreuzberg.embed(List.of("Hello world"), config);
+
+// Async variant
+CompletableFuture<float[][]> future = Kreuzberg.embedAsync(texts, null);
+```

docs/snippets/java/utils/token_reduction.md

@@ -0,0 +1,11 @@
+```java title="Java"
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.TokenReductionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .tokenReduction(TokenReductionConfig.builder()
+        .mode("moderate")
+        .preserveImportantWords(true)
+        .build())
+    .build();
+```

docs/snippets/java/utils/token_reduction_example.md

@@ -0,0 +1,22 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.TokenReductionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .tokenReduction(TokenReductionConfig.builder()
+        .mode("moderate")
+        .preserveImportantWords(true)
+        .build())
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("verbose_document.pdf", config);
+
+Object originalTokens = result.getMetadata().get("original_token_count");
+Object reducedTokens = result.getMetadata().get("token_count");
+Object reductionRatio = result.getMetadata().get("token_reduction_ratio");
+
+System.out.println("Reduced from " + originalTokens + " to " + reducedTokens + " tokens");
+System.out.println("Reduction: " + ((Number)reductionRatio).doubleValue() * 100 + "%");
+```