Nomad changes

docs/snippets/go/ocr/cloud_ocr_backend.md

@@ -0,0 +1,25 @@
+```go title="Go"
+package main
+
+import (
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+// The Go binding does not currently expose plugin OCR backend registration.
+// Use one of the built-in backends ("tesseract", "paddle-ocr", or VLM via "vlm").
+func main() {
+	result, err := kreuzberg.ExtractFileSync("scanned.pdf", nil, kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			Backend:  "tesseract",
+			Language: "eng",
+		},
+	})
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+
+	log.Println("content length:", len(result.Content))
+}
+```

docs/snippets/go/ocr/image_extraction.md

@@ -0,0 +1,32 @@
+```go title="Go"
+package main
+
+import (
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	extractImages := true
+	injectPlaceholders := true
+	autoAdjustDpi := true
+	targetDpi := int32(200)
+	maxDim := int32(2048)
+
+	result, err := kreuzberg.ExtractFileSync("document.pdf", nil, kreuzberg.ExtractionConfig{
+		Images: &kreuzberg.ImageExtractionConfig{
+			ExtractImages:      &extractImages,
+			TargetDpi:          &targetDpi,
+			MaxImageDimension:  &maxDim,
+			InjectPlaceholders: &injectPlaceholders, // set to false to extract images without markdown references
+			AutoAdjustDpi:      &autoAdjustDpi,
+		},
+	})
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+
+	log.Println("content length:", len(result.Content))
+}
+```

docs/snippets/go/ocr/image_preprocessing.md

@@ -0,0 +1,36 @@
+```go title="Go"
+package main
+
+import (
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	targetDpi := int32(300)
+	deskew := true
+	binarization := "otsu"
+
+	config := kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			TesseractConfig: &kreuzberg.TesseractConfig{
+				Preprocessing: &kreuzberg.ImagePreprocessingConfig{
+					TargetDpi:          &targetDpi,
+					Denoise:            true,
+					Deskew:             &deskew,
+					ContrastEnhance:    true,
+					BinarizationMethod: &binarization,
+				},
+			},
+		},
+	}
+
+	result, err := kreuzberg.ExtractFileSync("document.pdf", nil, config)
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+
+	log.Println("content length:", len(result.Content))
+}
+```

docs/snippets/go/ocr/ocr_easyocr.md

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

docs/snippets/go/ocr/ocr_elements.md

@@ -0,0 +1,34 @@
+```go title="Go"
+package main
+
+import (
+	"fmt"
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	cfg := kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			Backend:  "paddle-ocr",
+			Language: "en",
+		},
+	}
+
+	result, err := kreuzberg.ExtractFileSync("scanned.pdf", nil, cfg)
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+
+	for _, element := range result.OcrElements {
+		fmt.Printf("Text: %s\n", element.Text)
+		fmt.Printf("Confidence: %.2f\n", element.Confidence.Recognition)
+		fmt.Printf("Geometry: %+v\n", element.Geometry)
+		if element.Rotation != nil {
+			fmt.Printf("Rotation: %.1f°\n", element.Rotation.AngleDegrees)
+		}
+		fmt.Println()
+	}
+}
+```

docs/snippets/go/ocr/ocr_extraction.md

@@ -0,0 +1,24 @@
+```go title="Go"
+package main
+
+import (
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	cfg := kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			Backend:  "tesseract",
+			Language: "eng",
+		},
+	}
+
+	result, err := kreuzberg.ExtractFileSync("scanned.pdf", nil, cfg)
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+	log.Println(len(result.Content))
+}
+```

docs/snippets/go/ocr/ocr_force_all_pages.md

@@ -0,0 +1,24 @@
+```go title="Go"
+package main
+
+import (
+	"fmt"
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	result, err := kreuzberg.ExtractFileSync("document.pdf", nil, kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			Backend: "tesseract",
+		},
+		ForceOcr: true,
+	})
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+
+	fmt.Println(result.Content)
+}
+```

docs/snippets/go/ocr/ocr_multi_language.md

@@ -0,0 +1,23 @@
+```go title="Go"
+package main
+
+import (
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	result, err := kreuzberg.ExtractFileSync("multilingual.pdf", nil, kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			Backend:  "tesseract",
+			Language: "eng+deu+fra",
+		},
+	})
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+
+	log.Println(result.Content)
+}
+```

docs/snippets/go/ocr/ocr_paddleocr.md

@@ -0,0 +1,24 @@
+```go title="Go"
+package main
+
+import (
+	"log"
+
+	"github.com/kreuzberg-dev/kreuzberg/packages/go/v5"
+)
+
+func main() {
+	cfg := kreuzberg.ExtractionConfig{
+		Ocr: &kreuzberg.OcrConfig{
+			Backend:  "paddle-ocr",
+			Language: "en",
+		},
+	}
+
+	result, err := kreuzberg.ExtractFileSync("scanned.pdf", nil, cfg)
+	if err != nil {
+		log.Fatalf("extract failed: %v", err)
+	}
+	log.Println(len(result.Content))
+}
+```