API Endpoints - Document Classification
Welcome to the Extracta.ai Document Classification API. This section guides you through all available endpoints designed to help you classify uploaded documents into user-defined types and optionally extract structured data from them.
Whether you're automating invoice routing, separating receipts from contracts, or identifying CVs, this API gives you precise control over classification and downstream processing.
What is Document Classification?
Document Classification is the process of automatically assigning a document to a predefined category â such as an Invoice, Receipt, or Purchase Order â based on its content.
You define the categories (called Document Types), provide keywords, and optionally link them to extraction templates. Once classified, the document can automatically be parsed for structured data.
đ Available Endpoints
The Extracta.ai Classification API includes the following endpoints:
/createClassification
POST
/viewClassification
POST
/updateClassification
PATCH
/deleteExtraction
DELETE
/deleteBatch
DELETE
/deleteFiles
DELETE
/uploadFiles
POST
/getResults
POST
Each page covers detailed request and response formats.
đ§Š Document Types & Auto-Extraction
In classification, you define documentTypes
with:
A
name
anddescription
A list of
uniqueWords
to guide classification(Optionally) an
extractionId
to enable automatic structured data extraction if a match is found
Learn how to define these properly in the Document Types page.
đ Navigating the Documentation
Each endpoint in this section includes:
Request Parameters: Fields you can send in the API call
Response Objects: What to expect back
Examples: Realistic payloads to speed up integration
This structure ensures you can build confidently, whether you're uploading 10 documents or 10,000.
Last updated
Was this helpful?