Data extraction

How to successfully extract data from documents

Before extracting data you need to:

1. Create a document type

2. Build a dataset

3. Train the document type

Once you successfully completed the above steps, you can use the /extract-data endpoint to extract data. We prepared a sample code to help you out:

1 Open file as base64 string (Lines 4-6)

Open the file in a binary mode and correctly decode it into a base64 string. Make sure that your file is in the same directory as the script.

2 Create payload (Lines 8-12)

Create request payload with all the required parameters:

• file

• file_name

• document_type_name

3 Specify headers (Line 16-20)

Make sure that the Content-Type is set as application/json.

4 Authorize with your API key (Line 19)

You can get your API key at https://app.typless.com/settings/profile

5 Execute the request (Line 22)

Send the request and wait for the response.

Python

import requests
import base64

file_name = 'name_of_your_document.pdf'
with open(file_name, 'rb') as file:
    base64_data = base64.b64encode(file.read()).decode('utf-8')

payload = {
    "file": base64_data,
    "file_name": file_name,
    "document_type_name": "line-item-invoice"
}

url = "https://developers.typless.com/api/extract-data"

headers = {
    "Accept": "application/json",
    "Content-Type": "application/json",
    "Authorization": "<<apiKey>>"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.json())

Node

Response:

JSON

{
    "file_name": "name_of_your_document.pdf",
    "object_id": "1cb25cc8-c9fa-4149-9a83-b4ed6a2173b9",
    "extracted_fields": [
        {
            "name": "supplier",
            "values": [
                {
                    "x": -1,
                    "y": -1,
                    "width": -1,
                    "height": -1,
                    "value": "ScaleGrid",
                    "confidence_score": "0.968",
                    "page_number": -1
                }
            ],
            "data_type": "AUTHOR"
        },
        {
            "name": "invoice_number",
            "values": [
                {
                    "x": 1989,
                    "y": 545,
                    "width": 323,
                    "height": 54,
                    "value": "20190500005890",
                    "confidence_score": "0.250",
                    "page_number": 0
                },
                {
                    "x": 167,
                    "y": 574,
                    "width": 391,
                    "height": 54,
                    "value": "GB123456789",
                    "confidence_score": "0.250",
                    "page_number": 0
                }
            ],
            "data_type": "STRING"
        },
        {
            "name": "issue_date",
            "values": [
                {
                    "x": 2072,
                    "y": 628,
                    "width": 240,
                    "height": 54,
                    "value": "2019-06-05",
                    "confidence_score": "0.358",
                    "page_number": 0
                }
            ],
            "data_type": "DATE"
        },
        {
            "name": "total_amount",
            "values": [
                {
                    "x": 2146,
                    "y": 1196,
                    "width": 126,
                    "height": 54,
                    "value": "47.5300",
                    "confidence_score": "0.990",
                    "page_number": 0
                }
            ],
            "data_type": "NUMBER"
        }
    ],
    "line_items": [
        [
            {
                "name": "Description",
                "values": [
                    {
                        "x": 208,
                        "y": 1196,
                        "width": 1022,
                        "height": 50,
                        "value": "5/2019-MongoBackend-MgmtStandalone-Small-744 hours",
                        "confidence_score": "0.661",
                        "page_number": 0
                    }
                ],
                "data_type": "STRING"
            },
            {
                "name": "Price",
                "values": [
                    {
                        "x": 2146,
                        "y": 1196,
                        "width": 126,
                        "height": 54,
                        "value": "47.5300",
                        "confidence_score": "0.582",
                        "page_number": 0
                    }
                ],
                "data_type": "NUMBER"
            },
            {
                "name": "Quantity",
                "values": [
                    {
                        "x": 1979,
                        "y": 1196,
                        "width": 23,
                        "height": 54,
                        "value": "1",
                        "confidence_score": "0.647",
                        "page_number": 0
                    }
                ],
                "data_type": "NUMBER"
            }
        ]
    ],
    "customer": null
}

Supported file types

Typless supports the following file types:

• PDF

• JPG

• PNG

• TIFF

If you are working with scanned documents, we recommend using a resolution of 300 DPI to achieve optimal results.

🚧 Are you having problems with document quality?

We wrote a short blog on how to solve your problems here.

Line item extraction

If you want to extract line items, make sure you have defined the line-item structure in the document type.

Request parameters

Param	Type	Required	Details
document_type_name	string	YES	Name of the document type that you use for extraction.
file	string (Base64 encoded)	YES	The original file of the document that you are extracting data from.
file_name	string	YES	Name of the original file of the document that you are extracting data from. Name must include file type suffix, e.g., document.pdf
customer	string	NO	Your internal customer identification, used for .csv usage report. e.g., "my customer"

Understanding response

In the response, you will always find all of the fields you defined in the document type. Values for fields will be sorted by the confidence score. If the field is not present on the document, the value will be set to null.

Response base params

Param	Type	Details
file_name	string	Same value as provided in request
object_id	string	Id of document for sending feedback to dataset.
extracted_fields	list	List of extracted fields
customer	string	Same value as provided in request

Extracted fields params

Param	Type	Behaviour
name	string	Name of the field you defined in the document type
values	list	List of values for the field
data_type	string	Type of the field you defined in the document type

Extracted values params

Param	Type	Behaviour
x	int	Top left bounding box corner. If value is null this value will be -1
y	int	Top left bounding box corner. If value is null this bounding box corner value will be -1
width	int	Bounding box width. If value is null this width will be -1
height	int	Bounding box height. If value is null this height will be -1
value	string	Value for field in standard format
confidence_score	string	Value between 0 and 1. Bigger the value more confident the system is
page_number	int	Page on which value is present. If value is null this page number will be -1

📘 Field supplier_name will never carry any positional data - Just value!

All the positional parameters will always be -1, except for confidence_score and the value.

Example full response

JSON

{
    "file_name": "invoice_2.pdf",
    "object_id": "1cb25cc8-c9fa-4149-9a83-b4ed6a2173b9",
    "extracted_fields": [
        {
            "name": "supplier",
            "values": [
                {
                    "x": -1,
                    "y": -1,
                    "width": -1,
                    "height": -1,
                    "value": "ScaleGrid",
                    "confidence_score": "0.968",
                    "page_number": -1
                }
            ],
            "data_type": "AUTHOR"
        },
        {
            "name": "invoice_number",
            "values": [
                {
                    "x": 1989,
                    "y": 545,
                    "width": 323,
                    "height": 54,
                    "value": "20190500005890",
                    "confidence_score": "0.250",
                    "page_number": 0
                },
                {
                    "x": 167,
                    "y": 574,
                    "width": 391,
                    "height": 54,
                    "value": "GB123456789",
                    "confidence_score": "0.250",
                    "page_number": 0
                }
            ],
            "data_type": "STRING"
        },
        {
            "name": "issue_date",
            "values": [
                {
                    "x": 2072,
                    "y": 628,
                    "width": 240,
                    "height": 54,
                    "value": "2019-06-05",
                    "confidence_score": "0.358",
                    "page_number": 0
                }
            ],
            "data_type": "DATE"
        },
        {
            "name": "total_amount",
            "values": [
                {
                    "x": 2146,
                    "y": 1196,
                    "width": 126,
                    "height": 54,
                    "value": "47.5300",
                    "confidence_score": "0.990",
                    "page_number": 0
                }
            ],
            "data_type": "NUMBER"
        }
    ],
    "line_items": [
        [
            {
                "name": "Description",
                "values": [
                    {
                        "x": 208,
                        "y": 1196,
                        "width": 1022,
                        "height": 50,
                        "value": "5/2019-MongoBackend-MgmtStandalone-Small-744 hours",
                        "confidence_score": "0.661",
                        "page_number": 0
                    }
                ],
                "data_type": "STRING"
            },
            {
                "name": "Price",
                "values": [
                    {
                        "x": 2146,
                        "y": 1196,
                        "width": 126,
                        "height": 54,
                        "value": "47.5300",
                        "confidence_score": "0.582",
                        "page_number": 0
                    }
                ],
                "data_type": "NUMBER"
            },
            {
                "name": "Quantity",
                "values": [
                    {
                        "x": 1979,
                        "y": 1196,
                        "width": 23,
                        "height": 54,
                        "value": "1",
                        "confidence_score": "0.647",
                        "page_number": 0
                    }
                ],
                "data_type": "NUMBER"
            }
        ]
    ],
    "customer": null
}

Example null response:

JSON

{
    "file_name": "invoice.pdf",
    "object_id": "26e01d82-e7f4-48d3-a902-b74283b73279",
    "extracted_fields": [
        {
            "name": "total_amount",
            "values": [
                {
                    "x": -1,
                    "y": -1,
                    "width": -1,
                    "height": -1,
                    "value": null,
                    "confidence_score": "0.000",
                    "page_number": -1
                }
            ],
            "data_type": "NUMBER"
        },
        {
            "name": "invoice_number",
            "values": [
                {
                    "x": -1,
                    "y": -1,
                    "width": -1,
                    "height": -1,
                    "value": null,
                    "confidence_score": "0.000",
                    "page_number": -1
                }
            ],
            "data_type": "STRING"
        },
        {
            "name": "issue_date",
            "values": [
                {
                    "x": -1,
                    "y": -1,
                    "width": -1,
                    "height": -1,
                    "value": null,
                    "confidence_score": "0.000",
                    "page_number": -1
                }
            ],
            "data_type": "DATE"
        },
        {
            "name": "supplier",
            "values": [
                {
                    "x": -1,
                    "y": -1,
                    "width": -1,
                    "height": -1,
                    "value": null,
                    "confidence_score": "0.000",
                    "page_number": -1
                }
            ],
            "data_type": "AUTHOR"
        }
    ],
    "line_items": [],
    "customer": null
}