Nomad changes

docs/snippets/r/metadata/language_detection.md

@@ -0,0 +1,23 @@
+```r title="R"
+library(kreuzberg)
+
+result <- extract_file_sync("document.pdf")
+
+cat("Language Detection Results:\n\n")
+
+cat("Using direct field access:\n")
+cat("Detected Language:", result$detected_language, "\n\n")
+
+cat("Using S3 helper function:\n")
+lang <- detected_language(result)
+cat("Language (via helper):", lang, "\n\n")
+
+cat("Language Information:\n")
+if (lang == "en") {
+  cat("This is an English document\n")
+} else if (lang == "es") {
+  cat("This is a Spanish document\n")
+} else {
+  cat(sprintf("This is a %s document\n", lang))
+}
+```

docs/snippets/r/metadata/language_detection_multilingual.md

@@ -0,0 +1,13 @@
+```r title="R"
+library(kreuzberg)
+
+files <- c("english.pdf", "spanish.pdf", "french.pdf")
+config <- list(language_detection = list(enabled = TRUE))
+
+for (file in files) {
+  json <- extract_file_sync(file, "application/pdf", config)
+  result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+  cat(sprintf("%s: detected language = %s\n",
+              file, result$detected_language))
+}
+```

docs/snippets/r/metadata/metadata.md

@@ -0,0 +1,25 @@
+```r title="R"
+library(kreuzberg)
+
+result <- extract_file_sync("document.pdf")
+
+cat("Detected Language:", result$detected_language, "\n")
+cat("Quality Score:", result$quality_score, "\n")
+cat("Keywords:", paste(result$keywords, collapse=", "), "\n\n")
+
+cat("Metadata fields:\n")
+authors <- metadata_field(result, "authors")
+if (!is.null(authors)) {
+  cat("Authors:", paste(authors, collapse=", "), "\n")
+}
+
+created <- metadata_field(result, "created_date")
+if (!is.null(created)) {
+  cat("Created Date:", created, "\n")
+}
+
+pages_meta <- metadata_field(result, "page_count")
+if (!is.null(pages_meta)) {
+  cat("Pages:", pages_meta, "\n")
+}
+```

docs/snippets/r/metadata/page_boundaries.md

@@ -0,0 +1,22 @@
+```r title="R"
+library(kreuzberg)
+
+result <- extract_file_sync("document.pdf")
+
+boundaries <- result$metadata$pages$boundaries
+
+if (!is.null(boundaries) && length(boundaries) > 0L) {
+  content_bytes <- charToRaw(result$content)
+
+  for (i in seq_len(min(3L, length(boundaries)))) {
+    boundary <- boundaries[[i]]
+    page_bytes <- content_bytes[(boundary$byte_start + 1L):boundary$byte_end]
+    page_text <- rawToChar(page_bytes)
+    preview_end <- min(100L, nchar(page_text))
+
+    cat(sprintf("Page %d:\n", boundary$page_number))
+    cat(sprintf("  Byte range: %d-%d\n", boundary$byte_start, boundary$byte_end))
+    cat(sprintf("  Preview: %s...\n", substr(page_text, 1L, preview_end)))
+  }
+}
+```

docs/snippets/r/metadata/page_tracking_basic.md

@@ -0,0 +1,20 @@
+```r title="R"
+library(kreuzberg)
+
+result <- extract_file_sync("document.pdf")
+
+cat("Total pages:", page_count(result), "\n\n")
+
+for (i in seq_along(result$pages)) {
+  page <- result$pages[[i]]
+  cat(sprintf("Page %d:\n", i))
+  cat("  Elements:", length(page$elements), "\n")
+  cat("  Text content length:", nchar(page$content), "chars\n")
+
+  if (nchar(page$content) > 0L) {
+    preview <- substr(page$content, 1L, 100L)
+    cat(sprintf("  Preview: %s...\n", preview))
+  }
+  cat("\n")
+}
+```

docs/snippets/r/metadata/tables.md

@@ -0,0 +1,22 @@
+```r title="R"
+library(kreuzberg)
+
+result <- extract_file_sync("spreadsheet.xlsx")
+
+cat("Tables extracted:", length(result$tables), "\n\n")
+
+for (i in seq_along(result$tables)) {
+  table <- result$tables[[i]]
+  cat(sprintf("Table %d:\n", i))
+  cat("  Rows:", nrow(table), "\n")
+  cat("  Columns:", ncol(table), "\n")
+  cat("  Column names:", paste(colnames(table), collapse=", "), "\n")
+  cat("\n")
+
+  if (nrow(table) > 0L) {
+    cat("  Preview (first 3 rows):\n")
+    print(head(table, 3L))
+    cat("\n")
+  }
+}
+```

docs/snippets/r/metadata/vector_database_integration.md

@@ -0,0 +1,24 @@
+```r title="R"
+library(kreuzberg)
+
+config <- list(
+  chunking = list(max_characters = 1000L, overlap = 200L)
+)
+
+json <- extract_file_sync("document.pdf", "application/pdf", config)
+result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
+
+for (i in seq_len(min(3L, length(result$chunks)))) {
+  chunk <- result$chunks[[i]]
+  vector_doc <- list(
+    id = sprintf("doc_%d", i),
+    text = chunk,
+    metadata = list(
+      source = "document.pdf",
+      chunk_index = i,
+      length = nchar(chunk)
+    )
+  )
+  cat(sprintf("Vector DB entry %d: %d chars\n", i, nchar(chunk)))
+}
+```