How ADE Works
provides three APIs for document processing: Parse, Split, and Extract. Every workflow starts with Parse, which converts your documents into structured data. After parsing, you can optionally use Split to separate multi-document files or Extract to pull specific data fields.| API | Description | When to Use |
|---|---|---|
| Parse | Converts documents into structured Markdown with hierarchical JSON. Identifies elements like text, tables, and form fields with exact page and coordinate references. | Use to convert documents into structured data for downstream applications, such as RAG, search, and training LLMs. This is the required first step for all ADE workflows. |
| Split | Classifies and separates parsed documents into multiple sub-documents based on document types you define. | Use when one file contains multiple documents that need to be separated, such as batched Know Your Customer (KYC) documents. |
| Extract | Pulls specific data fields from parsed documents using schema-based extraction. | Use when you need the values for specific fields. Can be used after Parse or Split. |
Get Started
Demo ADE in the Playground
Create an account and process files in our Playground.
Call the API
Comfortable with using the Playground? Now you can make your first API call in minutes.
Key Features
Accurate results
Delivers high accuracy, even on complex documents. Achieved 99.16% accuracy on the DocVQA dataset.
Element detection
Identifies specific elements (called “chunks”) including text, tables, images, form fields, and bar codes.
Visual grounding
Includes page numbers and coordinates for each chunk to support traceability, validation, and compliance workflows.
Layout-agnostic parsing
Handles any document layout without templates or training—works out of the box.
Understands hierarchical relationships
Understands relationships between elements to generate accurate descriptions and maintain proper reading order.
Flexible output
Returns results in Markdown for human readability and JSON for programmatic access.
Supports multiple file types
Parses PDFs, images, text documents, presentations, and spreadsheets.
Supports multiple languages
Parses documents in multiple languages.