Nomad changes

docs/snippets/java/ocr/cloud_ocr_backend.md

@@ -0,0 +1,60 @@
+```java title="Java"
+import dev.kreuzberg.*;
+import java.lang.foreign.Arena;
+import java.lang.foreign.MemorySegment;
+import java.lang.foreign.ValueLayout;
+import java.net.http.*;
+import java.net.URI;
+
+public class CloudOcrExample {
+    public static void main(String[] args) {
+        Arena callbackArena = Arena.ofAuto();
+        String apiKey = "your-api-key";
+
+        OcrBackend cloudOcr = (imageBytes, imageLength, configJson) -> {
+            try {
+                // Read image bytes from native memory
+                byte[] image = imageBytes.reinterpret(imageLength)
+                    .toArray(ValueLayout.JAVA_BYTE);
+
+                // Read config JSON
+                String config = configJson.reinterpret(Long.MAX_VALUE)
+                    .getString(0);
+
+                // Call cloud OCR API
+                HttpClient client = HttpClient.newHttpClient();
+                HttpRequest request = HttpRequest.newBuilder()
+                    .uri(URI.create("https://api.example.com/ocr"))
+                    .header("Authorization", "Bearer " + apiKey)
+                    .POST(HttpRequest.BodyPublishers.ofByteArray(image))
+                    .build();
+
+                HttpResponse<String> response = client.send(request,
+                    HttpResponse.BodyHandlers.ofString());
+
+                String text = parseTextFromResponse(response.body());
+
+                // Return result as C string
+                return callbackArena.allocateFrom(text);
+            } catch (Exception e) {
+                return MemorySegment.NULL;
+            }
+        };
+
+        try (Arena arena = Arena.ofConfined()) {
+            Kreuzberg.registerOcrBackend("cloud-ocr", cloudOcr, arena);
+
+            // Use custom OCR backend in extraction
+            // Note: Requires ExtractionConfig with OCR enabled
+            ExtractionResult result = Kreuzberg.extractFileSync("scanned.pdf");
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+
+    private static String parseTextFromResponse(String json) {
+        // Parse JSON response and extract text field
+        return json; // Simplified
+    }
+}
+```

docs/snippets/java/ocr/image_extraction.md

@@ -0,0 +1,14 @@
+```java title="Java"
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.ImageExtractionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .imageExtraction(ImageExtractionConfig.builder()
+        .extractImages(true)
+        .targetDpi(200)
+        .maxImageDimension(2048)
+        .injectPlaceholders(true) // set to false to extract images without markdown references
+        .autoAdjustDpi(true)
+        .build())
+    .build();
+```

docs/snippets/java/ocr/image_preprocessing.md

@@ -0,0 +1,20 @@
+```java title="Java"
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.ImagePreprocessingConfig;
+import dev.kreuzberg.OcrConfig;
+import dev.kreuzberg.TesseractConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .ocr(OcrConfig.builder()
+        .tesseractConfig(TesseractConfig.builder()
+            .preprocessing(ImagePreprocessingConfig.builder()
+                .targetDpi(300)
+                .denoise(true)
+                .deskew(true)
+                .contrastEnhance(true)
+                .binarizationMethod("otsu")
+                .build())
+            .build())
+        .build())
+    .build();
+```

docs/snippets/java/ocr/ocr_easyocr.md

@@ -0,0 +1 @@
+EasyOCR is only available in Python.

docs/snippets/java/ocr/ocr_elements.md

@@ -0,0 +1,38 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.KreuzbergException;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.OcrConfig;
+import dev.kreuzberg.types.OcrElement;
+import java.io.IOException;
+
+public class Main {
+    public static void main(String[] args) {
+        try {
+            ExtractionConfig config = ExtractionConfig.builder()
+                .ocr(OcrConfig.builder()
+                    .backend("paddle-ocr")
+                    .language("en")
+                    .build())
+                .build();
+
+            ExtractionResult result = Kreuzberg.extractFile("scanned.pdf", config);
+
+            if (result.getOcrElements() != null) {
+                for (OcrElement element : result.getOcrElements()) {
+                    System.out.printf("Text: %s%n", element.getText());
+                    System.out.printf("Confidence: %.2f%n", element.getConfidence().getRecognition());
+                    System.out.printf("Geometry: %s%n", element.getGeometry());
+                    if (element.getRotation() != null) {
+                        System.out.printf("Rotation: %.1f°%n", element.getRotation().getAngle());
+                    }
+                    System.out.println();
+                }
+            }
+        } catch (IOException | KreuzbergException e) {
+            System.err.println("Extraction failed: " + e.getMessage());
+        }
+    }
+}
+```

docs/snippets/java/ocr/ocr_extraction.md

@@ -0,0 +1,26 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.KreuzbergException;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.OcrConfig;
+import java.io.IOException;
+
+public class Main {
+    public static void main(String[] args) {
+        try {
+            ExtractionConfig config = ExtractionConfig.builder()
+                .ocr(OcrConfig.builder()
+                    .backend("tesseract")
+                    .language("eng")
+                    .build())
+                .build();
+
+            ExtractionResult result = Kreuzberg.extractFile("scanned.pdf", config);
+            System.out.println(result.getContent());
+        } catch (IOException | KreuzbergException e) {
+            System.err.println("Extraction failed: " + e.getMessage());
+        }
+    }
+}
+```

docs/snippets/java/ocr/ocr_force_all_pages.md

@@ -0,0 +1,16 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.OcrConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .ocr(OcrConfig.builder()
+        .backend("tesseract")
+        .build())
+    .forceOcr(true)
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("document.pdf", config);
+System.out.println(result.getContent());
+```

docs/snippets/java/ocr/ocr_multi_language.md

@@ -0,0 +1,16 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.OcrConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .ocr(OcrConfig.builder()
+        .backend("tesseract")
+        .language("eng+deu+fra")
+        .build())
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("multilingual.pdf", config);
+System.out.println(result.getContent());
+```

docs/snippets/java/ocr/ocr_paddleocr.md

@@ -0,0 +1,27 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.KreuzbergException;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.OcrConfig;
+import java.io.IOException;
+
+public class Main {
+    public static void main(String[] args) {
+        try {
+            ExtractionConfig config = ExtractionConfig.builder()
+                .ocr(OcrConfig.builder()
+                    .backend("paddle-ocr")
+                    .language("en")
+                    // .paddleOcrConfig(PaddleOcrConfig.builder().modelTier("server").build()) // for max accuracy
+                    .build())
+                .build();
+
+            ExtractionResult result = Kreuzberg.extractFile("scanned.pdf", config);
+            System.out.println(result.getContent());
+        } catch (IOException | KreuzbergException e) {
+            System.err.println("Extraction failed: " + e.getMessage());
+        }
+    }
+}
+```