Split document
packets into individual
components

Split allows you to:

Separate a parsed document into multiple classified sub-documents.
Define your own classes via Split Rules.
Use the split results in your downstream workflows.

Your account comes with enough credits to Split several document packets.

The Problem

Who Uses Split?

Financial institutions and insurers that receive PDFs containing multiple document types for a single customer or application.

Healthcare systems ingesting patient records received as batched PDFs.

Accounting departments processing PDFs containing multiple invoices and receipts.

Organizations managing product catalogs where one PDF contains specifications for multiple products.

The Solution

Not all document splitters created equal.

LLM prompting works for simple cases, but production pipelines break for very long documents or when there are hundreds of classes to detect. ADE Split is built for that reality — handling the full complexity of enterprise documents without manual intervention or silent failures.

Quantity of Classes

Define hundreds of sub-document classes such as resume, invoice, pay stub, credit report, etc.

Subdivide within a Class

Provide an identifier to separate pay stubs by date, invoices by vendor, or credit scores by name.

Scales to Production

Create a reusable pipeline to Parse, then Split, then Extract from each sub-document type found at scale.

What you get

No fine-tuning or templates required
Agentic system that plans and executes
Developer friendly APIs

Returns clean JSON
Document class detection
Page ranges for document class

Works across languages
Handles hundreds of pages
Searches for hundreds of classes

Subdivides based on identifiers
Works seamlessly with Parse
Works seamlessly with Extract

Document gallery

Built for complex, real-world documents.

Starting PDFs with hundreds of pages. Categorization schemas with hundreds of classes. Split can handle it.

Read the Docs for Split →

UI and API

Prototype in the UI. Scale with the API.

Use the Agentic Document Extraction Visual Playground for rapid prototyping and experimentation.

Then transition seamlessly to the REST API, Python library, or TypeScript library. Split is in Preview.

Provide our Agent Skills directly to agentic coding assistants to accelerate your development.

cURL

curl -X POST 'https://api.va.landing.ai/v1/ade/split' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'markdown=@markdown.md' \
  -F 'split_class=[{
        "name": "name",
        "description": "description",
        "identifier": "identifier"
      }]' \
  -F 'model=split-latest'

Python

split_class = [
    {
        "name":"Bank Statement", 
        "description": "Description goes here."
    },
    {
        "name": "Pay Stub",
        "description": "Description goes here",
        "identifier": "Pay Stub Date",
    }
]
split_response = client.split(
    split_class=json.dumps(split_class),
    markdown=parse_response.markdown,  
    model="split-latest",
)