structural (default)

structural produces one chunk per structural element: each heading, paragraph, table, and list becomes its own chunk. It's the finest-grained mode and the best choice when you want element-level control over indexing.

from py_chunks import get_chunks

chunks = get_chunks("report.docx", mode="structural")

default vs structural

For most formats, default is element-level chunking.

• DOCX: default is normalized to structural — they're equivalent.
• PDF: default and structural are not the same. default uses a fast, lightweight path; structural uses the full, font-size-weighted layout analysis. Use structural when heading detection matters.

content_type values

Chunks are typed by what they contain — common values include heading, plain_paragraph, bullet_list, table, and code_block. See the full list in the Output Schema.

When to use it

• Fine-grained retrieval where each element should be independently searchable.
• Downstream logic that re-groups elements itself.
• Precise citations back to a single paragraph or table.