fil/docs/snippets/r/config/ocr_configuration.md

library(kreuzberg)

# Configure OCR with Tesseract
config <- list(
  force_ocr = TRUE,
  ocr = list(
    backend = "tesseract",
    language = "eng+deu"
  )
)

json <- extract_file_sync("scanned_document.pdf", "application/pdf", config)
result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
cat(result$content)