Files
fil/docs/snippets/r/advanced/chunk_page_mapping.md
Henrik Jess Nielsen b4c07d3693
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Nomad changes
2026-06-01 23:40:55 +02:00

28 lines
789 B
Markdown

```r title="R"
library(kreuzberg)
config <- list(
chunking = list(max_characters = 500L, overlap = 50L),
pages = list(extract_pages = TRUE)
)
json <- extract_file_sync("document.pdf", "application/pdf", config)
result <- jsonlite::fromJSON(json, simplifyVector = FALSE)
for (i in seq_along(result$chunks)) {
chunk <- result$chunks[[i]]
metadata <- result$chunk_metadata[[i]]
if (!is.null(metadata$first_page) && !is.null(metadata$last_page)) {
page_range <- if (metadata$first_page == metadata$last_page) {
sprintf("Page %d", metadata$first_page)
} else {
sprintf("Pages %d-%d", metadata$first_page, metadata$last_page)
}
preview <- substr(chunk, 1L, min(50L, nchar(chunk)))
cat(sprintf("Chunk: %s... (%s)\n", preview, page_range))
}
}
```