Parsing
Markdown Response
When you parse a document with the API, the extracted data is returned as Markdown following the format below.
Corresponding JSON Object | Description | Example |
---|---|---|
chunk_type | The element type | title |
grounding | The page number (starting at 0) and relative coordinates of the element on that page | from page 0 (l=0.074,t=0.112,r=0.444,b=0.147) |
chunk_id | The unique ID assigned to the chunk | with ID 83765a10-0d93-4b1d-9473-83c90ad10798 |