Start

Turn a single document to data without a workflow, ad-hoc.

post

Send an agent to extract data from a document, optionally transforming it to a specific data schema. POST a file called 'file'. Must be a filetype readable from the dashboard document task (ie pdf or image)

Authorizations

Query parameters

additional_instructionsstringOptional

Additional hints to the AI about what you want to extract

Example: I want a list of people

modelstring · enumOptional

The model to use. Large is slower but may be more accurate. Small is faster but may be less accurate.

Possible values:

extendedbooleanOptional

Attempt to extract extended metadata, like URLs and images

cap_screenshotsintegerOptional

Increasing this will cause the AI to scroll further down the page

Default: 5

Body

application/jsonmultipart/form-data

stringOptional

A JSON schema to extract against

Example: {"schema":{"name":"<the site name>"}}

Responses

post

HTTPcURLJavaScriptPython

POST /api/v2/document/start HTTP/1.1
Host: api.jsonify.com
Authorization: Bearer JWT
Content-Type: application/json
Accept: */*
Content-Length: 37

{
  "schema": {
    "name": "<the site name>"
  }
}

application/jsonmultipart/form-data

200

An in-progress result, which you can retrieve later with /result/{result_id}

{
  "message": "started",
  "result": {
    "id": "e4ab8b5b-45bd-4e0f-8abb-5ce8a4db255e"
  },
  "success": true
}