This commit is contained in:
24
docs/snippets/r/advanced/vector_database_integration.md
Normal file
24
docs/snippets/r/advanced/vector_database_integration.md
Normal file
@@ -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)))
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user