Nomad changes

docs/snippets/r/ocr/cloud_ocr_backend.md

@@ -0,0 +1,19 @@
+```r title="R"
+library(kreuzberg)
+
+custom_ocr_backend <- function(image_path, language) {
+  cat(sprintf("Processing image: %s\n", image_path))
+  return(sprintf("Extracted text from %s", image_path))
+}
+
+register_ocr_backend("custom_cloud", custom_ocr_backend)
+
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "custom_cloud", language = "en")
+)
+
+json <- extract_file_sync("document.pdf", "application/pdf", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+cat(sprintf("Custom backend result: %d chars\n", nchar(result$content)))
+```

docs/snippets/r/ocr/image_extraction.md

@@ -0,0 +1,16 @@
+```r title="R"
+library(kreuzberg)
+
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "tesseract", language = "eng")
+)
+
+json <- extract_file_sync("scan.png", "image/png", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat("Image extraction via OCR:\n")
+cat(sprintf("Content length: %d characters\n", nchar(result$content)))
+cat(sprintf("Mime type: %s\n", result$mime_type))
+cat(sprintf("Detected language: %s\n", result$detected_language))
+```

docs/snippets/r/ocr/image_preprocessing.md

@@ -0,0 +1,16 @@
+```r title="R"
+library(kreuzberg)
+
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "tesseract", language = "eng"),
+  enable_quality_processing = TRUE
+)
+
+json <- extract_file_sync("scan.png", "image/png", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat(sprintf("Quality: %.2f, Length: %d\n",
+            result$quality_score %||% 0,
+            nchar(result$content)))
+```

docs/snippets/r/ocr/ocr_easyocr.md

@@ -0,0 +1,16 @@
+```r title="R"
+library(kreuzberg)
+
+# Note: EasyOCR backend requires Python to be installed
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "easyocr", language = "en")
+)
+
+json <- extract_file_sync("document.pdf", "application/pdf", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat("EasyOCR extraction:\n")
+cat(sprintf("Content length: %d characters\n", nchar(result$content)))
+cat(sprintf("Detected language: %s\n", result$detected_language))
+```

docs/snippets/r/ocr/ocr_elements.md

@@ -0,0 +1,23 @@
+```r title="R"
+library(kreuzberg)
+
+# Enable structured OCR elements alongside text extraction
+config <- list(
+  ocr = list(
+    backend = "paddleocr",
+    language = "en",
+    element_config = list(include_elements = TRUE)
+  )
+)
+
+json <- extract_file_sync("scanned.pdf", "application/pdf", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+if (!is.null(result$ocr_elements)) {
+  for (element in result$ocr_elements) {
+    cat(sprintf("Text: %s\n", element$text))
+    cat(sprintf("Confidence: %.2f\n", element$confidence$recognition))
+    cat("\n")
+  }
+}
+```

docs/snippets/r/ocr/ocr_extraction.md

@@ -0,0 +1,17 @@
+```r title="R"
+library(kreuzberg)
+
+# Configure Tesseract OCR
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "tesseract", language = "eng")
+)
+
+# Extract text from a scanned image
+json <- extract_file_sync("scan.png", "image/png", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat(sprintf("Extracted %d characters\n", nchar(result$content)))
+cat("Content preview:\n")
+cat(substr(result$content, 1, 200))
+```

docs/snippets/r/ocr/ocr_force_all_pages.md

@@ -0,0 +1,12 @@
+```r title="R"
+library(kreuzberg)
+
+config <- list(force_ocr = TRUE)
+
+json <- extract_file_sync("multipage_document.pdf", "application/pdf", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat(sprintf("Total pages: %d\n", length(result$pages)))
+cat(sprintf("Content extracted via OCR: %d characters\n", nchar(result$content)))
+cat(sprintf("Detected language: %s\n", result$detected_language))
+```

docs/snippets/r/ocr/ocr_multi_language.md

@@ -0,0 +1,18 @@
+```r title="R"
+library(kreuzberg)
+
+# Configure multi-language OCR (English, French, German)
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "tesseract", language = "eng+fra+deu")
+)
+
+# Extract from a multilingual document
+json <- extract_file_sync("multilingual.png", "image/png", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat(sprintf("Detected language: %s\n", result$detected_language))
+cat(sprintf("Extracted %d characters\n", nchar(result$content)))
+cat("Content preview:\n")
+cat(substr(result$content, 1, 200))
+```

docs/snippets/r/ocr/ocr_paddleocr.md

@@ -0,0 +1,18 @@
+```r title="R"
+library(kreuzberg)
+
+# Configure PaddleOCR backend (defaults to mobile tier)
+config <- list(
+  force_ocr = TRUE,
+  ocr = list(backend = "paddle-ocr", language = "en")
+)
+
+# Extract text from an image using PaddleOCR
+json <- extract_file_sync("document.jpg", "image/jpeg", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+cat(sprintf("Extracted %d characters\n", nchar(result$content)))
+cat(sprintf("MIME type: %s\n", result$mime_type))
+cat("Content preview:\n")
+cat(substr(result$content, 1, 200))
+```