Overview

The Split API splits  e.g. scan batches. The service receives a pdf which includes more than one business documents and returns a json including the definition what page within the pdf is a start of a document (first page).

API Description:

The interface accepts pdf file only.
For now the number of pages is restricted to 100.
The AI service classifies each page in the pdf file if it is a “First” or “Other” page.
Service Endpoint: htttps://api.bludelta.ai/doc-splitter/v1/doc-splitter
The API key http header as for the Classyfier (X-APIKEY) will be required for a successful https request.

If you need a key pls contact: office@blumatix.com

Response JSON Example:

[
{
"Page": 1,
"Class": "First",
"Score": 0.32
},
{
"Page": 2,
"Class": "Other",
"Score": 0.32
},
{
"Page": 3,
"Class": "First",
"Score": 0.32
}
]

Response YAML Endpoint description:

openapi: 3.0.0
info:
title: Document Splitter API
description: An API for classification of split marks within a pdf consisting of many docs
version: 1.0.0
servers: - url: https://api.bludelta.ai
paths: /doc-splitter:
post:
summary: An API for classification of split marks within a pdf consisting of many docs
requestBody:
required: true
content:
application/pdf:
schema:
type: string
format: binary
responses:
'200':
description: OK
content:
application/json:
schema:
type: array
items:
type: object
properties:
Page:
type: integer
Class:
type: string
Score:
type: number
'400':
description: Bad Request
'500':
description: Internal Server Error