DocumentChunking splits documents on paragraph and sentence boundaries.
DocumentChunking first splits text at blank-line paragraph boundaries. It splits paragraphs above the target chunk_size at sentence boundaries, then prepends the configured overlap.
Parameter
Type
Default
Description
chunk_size
int
5000
Target size before overlap. A single long sentence or added overlap can produce a larger chunk.
overlap
int
0
The number of characters to overlap between chunks.
