This commit is contained in:
23
docs/snippets/r/advanced/embedding_with_chunking.md
Normal file
23
docs/snippets/r/advanced/embedding_with_chunking.md
Normal file
@@ -0,0 +1,23 @@
|
||||
```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)
|
||||
|
||||
cat(sprintf("Preparing %d chunks for embedding:\n", length(result$chunks)))
|
||||
|
||||
embeddings_data <- list()
|
||||
for (i in seq_along(result$chunks)) {
|
||||
embeddings_data[[i]] <- list(
|
||||
chunk_id = i,
|
||||
text = result$chunks[[i]],
|
||||
length = nchar(result$chunks[[i]])
|
||||
)
|
||||
}
|
||||
|
||||
cat(sprintf("Ready to embed %d chunks\n", length(embeddings_data)))
|
||||
```
|
||||
Reference in New Issue
Block a user