The Block Object
Detailed information about the Block object structure and types returned by the /parse
API endpoint.
Overview
A Block represents a distinct content element within a document, such as a paragraph of text, a heading, a table, or a figure. Blocks are the fundamental units that make up chunks in parsed documents.
Block Object Structure
The type of object. Always “block”.
A unique identifier for the block, deterministically generated as a hash of the block content.
The type of block. Possible values include:
text
: Regular text contentheading
: Section or document headingssection_heading
: Subsection headingstable
: Tabular data with rows and columnsfigure
: Images, charts, or diagrams
The textual content of the block, formatted according to the target format specified in the parse request.
Additional details specific to the block type. The structure varies depending on the block type.
Block Type Details
Figure Details
Indicates this is a figure details object.
URL to the clipped/segmented figure image. Only set if the option figureImageClippingEnabled
is true (which is default true).
The refined type of figure - only set when figure classification and summarization is enabled. Possible values:
image
: A photographic imagechart
: A data chart or graphdiagram
: A schematic or diagramlogo
: A company or brand logoother
: Any other type of figure
Table Details
Indicates this is a table details object.
The number of rows in the table.
The number of columns in the table.
Metadata about the block.
properties
The page number where the block appears in the document.
An array of points defining the polygon that bounds the block on the page.
Each point is an object with x
and y
coordinates.
A simplified rectangular bounding box for the block, derived from the polygon.
properties
The y-coordinate of the top edge of the bounding box.
The x-coordinate of the left edge of the bounding box.
The width of the bounding box.
The height of the bounding box.