Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.aryn.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Introduction

In this tutorial, we will walk through an example of using DocParse to suggest properties for a document. This is useful when you want to either pick properties to extract automatically or have some properties to start with when using a human-in-the-loop approach. We will be working with a sample insurance document that contains a workers compensation reinsurance submission.
By the end of this tutorial, you will be able to generate a schema with properties like the one below for a document using the Aryn SDK. 
{
    "schema": {
        "properties": [
            {
                "name": "submission_date",
                "type": {
                    "type": "date",
                    "required": false,
                    "description": "The date the submission was made",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        "2026-09-15"
                    ],
                    "source": null,
                    "validators": [],
                }
            },
            {
                "name": "umr",
                "type": {
                    "type": "string",
                    "required": false,
                    "description": "Unique Market Reference for the submission",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        "G240915X8E3451"
                    ],
                    "source": null,
                    "validators": []
                }
            },
            {
                "name": "reinsured",
                "type": {
                    "type": "object",
                    "required": false,
                    "description": "Information about the reinsured company",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        {
                            "address": "123 Summit Way, Denver, CO 80202, UNITED STATES",
                            "name": "Pinnacle National Insurance Co."
                        }
                    ],
...

​
Prerequisites

  1. Get your free Aryn API key by signing up on the Aryn Console at app.aryn.ai.
  2. Download the sample document or have your own handy.

​
Extracting a Schema with Suggest Properties

To extract a schema with suggested properties, you can use the suggest_properties field of the property_extraction_options dictionary in the partition_file function, like so: 
from aryn_sdk.partition import partition_file
import json

data = partition_file(
    "gri.pdf",
    property_extraction_options={"suggest_properties": True}
)

print(json.dumps(data, indent=4))
Running this will return a dictionary with the elements and suggested properties. 
{
    "status": [...],
    "status_code": 200,
    "elements": [...],
    "schema": {
        "properties": [
            {
                "name": "submission_date",
                "type": {
                    "type": "date",
                    "required": false,
                    "description": "The date the submission was made",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        "2026-09-15"
                    ],
                    "source": null,
                    "validators": [],
                }
            },
            {
                "name": "umr",
                "type": {
                    "type": "string",
                    "required": false,
                    "description": "Unique Market Reference for the submission",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        "G240915X8E3451"
                    ],
                    "source": null,
                    "validators": []
                }
            },
            {
                "name": "reinsured",
                "type": {
                    "type": "object",
                    "required": false,
                    "description": "Information about the reinsured company",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        {
                            "address": "123 Summit Way, Denver, CO 80202, UNITED STATES",
                            "name": "Pinnacle National Insurance Co."
                        }
                    ],
                    "source": null,
                    "validators": [],
                    "properties": [
                        {
                            "name": "name",
                            "type": {
                                "type": "string",
                                "required": false,
                                "description": "Name of the reinsured company",
                                "default": null,
                                "extraction_instructions": null,
                                "examples": null,
                                "source": null,
                                "validators": []
                            }
                        },
                        {
                            "name": "address",
                            "type": {
                                "type": "string",
                                "required": false,
                                "description": "Address of the reinsured company",
                                "default": null,
                                "extraction_instructions": null,
                                "examples": null,
                                "source": null,
                                "validators": []
                            }
                        }
                    ]
                }
            },
            {
                "name": "original_insured",
                "type": {
                    "type": "object",
                    "required": false,
                    "description": "Information about the original insured company",
                    "default": null,
                    "extraction_instructions": null,
                    "examples": [
                        {
                            "address": "4500 Industrial Blvd, Chicago, IL 60632",
                            "name": "Apex Logistics & Distribution"
      ...
    },
}