Whatever message this page gives is out now! Go check it out!
split
Last update:
May 18, 2026
Splits an Array of document Structs into smaller text segment Structs using the specified chunking strategy. The resulting segments are suitable for embedding and vector store ingestion.
Syntax
docService.split( documents [, options] )Parameters
Parameter | Type | Required | Description |
|---|---|---|---|
documents | Array | Required | Array of document Structs as returned by load(). |
options | Struct | Optional | Splitting configuration. Keys: splitterType (String, default "recursive": valid values: recursive, paragraph, sentence, line, character, word, regex); chunkSize (Numeric, default 1000); chunkOverlap (Numeric, default 100); separators (Array of String, for recursive splitter); regexPattern (String, required when splitterType = "regex"). |
Returns
Returns an Array of text segment Structs, each with:
text (String) and metadata (Struct).Example
segments = docService.split(documents, {
splitterType: "recursive",
chunkSize: 1000,
chunkOverlap: 100
});
writeOutput("Created #arrayLen(segments)# segments");
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Share additional feedback to help us improve.
0/255
|
