Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.landing.ai/llms.txt

Use this file to discover all available pages before exploring further.

The new Parse API is a redesign, not a version bump. The request you send changes very little, but the response is a new shape built around . Plan to rewrite the code that reads the parse response; there is no field-for-field mapping from the generally available (GA) Parse API. This guide covers what changed and what to update. For the full response reference, see How Parse Works.
This is a Preview release. Don’t use it in production. See Important to Know for details. To learn more about the generally available (GA) version of ADE, go to ADE Overview.

​
Confirm Your Input Formats

The Preview accepts PDFs and images only. If your pipeline depends on Office formats supported by the GA Parse API (Word, PowerPoint, spreadsheets), keep those workflows on the GA Parse API. See Supported File Types.

​
What Changes at a Glance

  • Your request: mostly the same. A new endpoint, two removed parameters, and one new options parameter.
  • Your response: new. Flat chunks become a hierarchical structure tree, grounding coordinates change units, and the Markdown for visuals is simpler.
  • Other ADE APIs: ADE Extract and ADE Section expect the GA response shape. If your workflow chains Parse with either, keep those workflows on the GA Parse API for now.

​
Update Your Request

The request contract is close to the GA API. Update the endpoint and adjust a few parameters.
AspectGA Parse API ()Preview Parse API ()
EndpointPOST /v1/ade/parsePOST /v2/ade/parse
AuthenticationBearer API keyBearer API key (unchanged)
File inputdocument or document_urldocument or document_url (unchanged)
Model selectionmodel form fieldmodel form field (unchanged)
Page or section splittingsplit form fieldRemoved. Use options.pages to select pages to process.
Figure promptscustom_prompts form fieldRemoved.
Output customizationNot functionaloptions: select pages, set table format, toggle captions, control grounding detail.
See Request Options for the full options schema.

​
Rework Your Response Handling

This is where the work is. The top-level response fields are different, and the concepts behind them changed.

​
Chunks Are Now Elements

The GA API returns a flat chunks array, where each chunk carries its own markdown and inline grounding. replaces this with a hierarchical structure tree: a document whose children are pages, and each page’s children are the elements on that page. Tables nest their cells (td and th) as children. Elements no longer carry their own Markdown or coordinates. Instead, each element has a span (a [start, end) range into the top-level markdown string) and an id you use to look up its location in the top-level grounding map.

​
Grounding Moved and Changed

In the GA API, grounding lived both inline on each chunk and in a top-level grounding map. In , grounding lives only in the top-level grounding map, keyed by element id. Three things changed about the values:
  • Coordinates are integers in page units. The GA API used normalized floats from 0 to 1. uses integer points (pt) for PDFs and integer pixels (px) for images, as [left, top, right, bottom]. To draw or compare boxes, read the page’s width, height, and unit from structure rather than assuming a 0-to-1 range.
  • Line-level detail through parts. Each grounding entry adds a parts array. For text and marginalia, there is one part per visual line, so you can highlight or extract at the line level. Other element types return an empty parts array.
  • No confidence score. The GA confidence and low_confidence_spans fields are removed.

​
Markdown Is Cleaner

The GA API wrapped visual elements in non-standard tags (for example, <::logo: ...::>) and embedded long generated descriptions. uses standard Markdown:
  • Visual elements use image syntax. Figures and logos render as ![label], where the label is a short description or a classification subtype such as ![CHART]. See Figure and Attestation Labels.
  • Page breaks are explicit. A <!-- page --> comment separates each page’s content (absent in single-page documents).
  • Tables and math are standardized. Tables use pipe syntax by default (set options.elements.table.format="html" for HTML), and math uses $$...$$ (block) and $...$ (inline).
The GA API duplicated Markdown onto every chunk. returns the Markdown once, as the top-level markdown string, and every element points into it with a span of Unicode code point offsets [start, end). To get an element’s text, slice the Markdown string with its span. This is the main mental shift: structure and grounding describe positions in one shared Markdown document rather than carrying their own copies of the text.

​
What Was Removed

These GA fields and parameters have no equivalent in :
  • chunks and the per-chunk markdown (use structure and span slices instead)
  • splits and the split parameter
  • custom_prompts
  • confidence and low_confidence_spans
  • Normalized 0-to-1 coordinates
  • Inline per-chunk grounding

​
Migration Checklist

  • Point requests at POST /v2/ade/parse.
  • Remove the split and custom_prompts parameters; add options if you need page selection or output control.
  • Stop reading chunks. Walk structure.children (pages) and their children (elements) instead.
  • Look up each element’s location by id in the top-level grounding map.
  • Rescale bounding boxes: switch from normalized floats to integer pt/px, using the page’s width, height, and unit.
  • Slice the top-level markdown with each element’s span to recover its text.
  • Remove any logic that depends on confidence or low_confidence_spans.
  • Update visual-element handling for ![label] image syntax instead of <:: ... ::> tags.