VAT invoice

Extracting metadata and VAT rates from invoices with examples in Python and Node.

Overview

This guide covers how to extract metadata and VAT rates from supplier invoices with examples in Python and Node.

You will extract the following metadata fields:

Name of the supplier
Name of the receiver
Invoice number
Purchase order number
Issue date
Pay due date
Total amount
Net amount

You will extract the following VAT rate fields:

VAT rate percentage
VAT rate net

This guide shows you how to

Getting your API Key

The Authorization header for your API key is: Token YOUR-API-KEY (Login if you do not see one). You can also obtain the API key by visiting the Settings page.

1. Create a new document type

Before you start extracting data, you need to define a document type. Navigate to the Dashboard page and click on the New document type button in the top right corner of the table. Next, select the VAT invoice card. The wizard will already pre-fill all the needed extraction fields along with the document type configuration. Click on the Create document type.

This will create a new document type named vat-invoice with the following fields:

supplier_name
invoice_number
purchase_order_number
receiver_name
issue_date
pay_due_date
total_amount
net_amount

The document type will have a VAT rate plugin already set up for your fields.

2. Add suppliers

Typless is a tool for automation. That's why you need to fill the dataset and train it first. To automate a new supplier, you first need to add its invoices to the data set. Download an example invoice from Best Flowers Inc:

Best Flowers Inc. - download

To add a document to the dataset, use the add-document endpoint or use the training room, where you can easily upload a file and fill out the necessary information.

The dataset is created by uploading an original file with the correct value for each field defined inside the document type. A key point to note regarding VAT invoices is that you must also fill out all the VAT rates listed on the document, so the engine will take these into account the next time it performs extraction.

1 Open file as base 64 string (Lines 6-9)

Open the file and encode it as a base64 String. Make sure you are pointing to the directory with the file.

2 Specify payload (Lines 11-72)

Specify your payload with the required fields:

file - base64 encoded file
file_name - name of the file
document_type_name - the name of the document type we want to add the supplier to
learning_fields - fields with the correct values used for training
vat_rates

3 VAT rates payload property (Lines 49-71)

The vat_rates property represents all the VAT rates present on the document. A VAT rate is represented with a list of field structures with a vat_rate_percentage field and a vat_rate_net field.

4 Specify headers (Lines 76-80)

Add all the required request headers.

5 Send the request (Lines 82-84)

Send the request and make sure that everything went smoothly.

import json

import requests
import base64

file_name = 'vat_invoice_1.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": "vat-invoice",
    "learning_fields": [
        {
            "name": "supplier_name",
            "value": "Best flowers Inc."
        },
        {
            "name": "receiver_name",
            "value": "James Bond"
        },
        {
            "name": "invoice_number",
            "value": "123/2017"
        },
        {
            "name": "purchase_order_number",
            "value": "001-001-30"
        },
        {
            "name": "pay_due_date",
            "value": "2017-06-30"
        },
        {
            "name": "issue_date",
            "value": "2017-06-16"
        },
        {
            "name": "total_amount",
            "value": "735.3300"
        },
        {
            "name": "net_amount",
            "value": "644.1400"
        }
    ],
    "vat_rates": [
        [
            {
                "name": "vat_rate_percentage",
                "value": "9.5000"
            },
            {
                "name": "vat_rate_net",
                "value": "404.1400"
            },
        ],
        [
            {
                "name": "vat_rate_percentage",
                "value": "22.0000"
            },
            {
                "name": "vat_rate_net",
                "value": "240.0000"
            },
        ]

    ]
}

url = "https://developers.typless.com/api/add-document"

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

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

print(response.json())

const fetch = require('node-fetch');
const fs = require('fs');

const fileName = 'vat_invoice_1.pdf';
const base64File = fs.readFileSync(fileName, {encoding: 'base64'});

const url = 'https://developers.typless.com/api/add-document';

const payload = {
    file: base64File,
    file_name: fileName,
    document_type_name: "vat-invoice",
    learning_fields: [
        {
            "name": "supplier_name",
            "value": "Best flowers Inc."
        },
        {
            "name": "receiver_name",
            "value": "James Bond"
        },
        {
            "name": "invoice_number",
            "value": "123/2017"
        },
        {
            "name": "purchase_order_number",
            "value": "001-001-30"
        },
        {
            "name": "pay_due_date",
            "value": "2017-06-30"
        },
        {
            "name": "issue_date",
            "value": "2017-06-16"
        },
        {
            "name": "total_amount",
            "value": "735.3300"
        },
        {
            "name": "net_amount",
            "value": "644.1400"
        }
    ],
    vat_rates: [
        [
            {
                "name": "vat_rate_percentage",
                "value": "9.5000"
            },
            {
                "name": "vat_rate_net",
                "value": "404.1400"
            },
        ],
        [
            {
                "name": "vat_rate_percentage",
                "value": "22.0000"
            },
            {
                "name": "vat_rate_net",
                "value": "240.0000"
            },
        ]

    ]
};

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

let options = {
    method: 'POST',
    headers: headers,
    body: JSON.stringify(payload)
};

fetch(url, options)
    .then(res => res.json())
    .then(json => console.log(json))
    .catch(err => console.error('error:' + err));

Response:

{
  details: [ '0d0596ac5e7320eb9b75ee1b327dff4d899f1a6a' ],
  message: 'Document added successfully.'
}

As you can see, to achieve high accuracy, Typless only needs the values that are in the document. Nevertheless, there are some rules to keep in mind when providing values.

Applying these rules to the provided example, you will change some fields:

total_amount value was converted with number type rules from 735,33 to 735.3300
net_amount value was converted with number type rules from 644,14 to 644.1400
issue_date value was converted with date type rules from 16.06.2017 to 2017-06-16
pay_due_date value was converted with date type rules from 30.06.2017 to 2017-06-30

You also applied the same rules to the VAT rates on the document. VAT rates are structured as a list of lists, similarly to line items, so keep that in mind when building the data structure for training.

Do you need more information on the VAT rate plugin? Learn more about how it works and its limitations here.

You will have one supplier added to your document type after you run the code example.

3. Execute training

👍 Training is executed automatically every day at 10 PM CET

For all of your suppliers with new documents in the dataset of all your document types. Free of charge

To immediately see results, you can trigger the training process on the Dashboard page. Look for the VAT-invoice document type in the list, and click on .

Need more information about training? Read more about it here.

4. Extract data from documents

After the training is finished, you can start precisely extracting data from documents from trained suppliers. Download a new example from Best Flowers Inc:

Best Flowers Inc. 2 - download

Download it and extract the data using the code:

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

Open the file in 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 8-11)

Create request payload with all the required parameters:

file
file_name
document_type_name

3 Specify headers (Lines 16-19)

Make sure that the Content-Type is set as application/json. Fill the Authorization header with your API key.

4 Execute the request (Line 22)

Send the request and wait for the extraction to finish.

import requests
import base64

file_name = 'vat_invoice_2.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": "vat-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)

for field in response.json()['extracted_fields']:
    print(f'{field["name"]}: {field["values"][0]["value"]}')

print('--- VAT RATES ---')

for vat_rate in response.json()['vat_rates']:
    for field in vat_rate:
        print(f'{field["name"]}: {field["values"][0]["value"]}')
    print('----------------------------------')

const fetch = require('node-fetch');
const fs = require('fs');

const fileName = 'vat_invoice_2.pdf';
const base64File = fs.readFileSync(fileName, {encoding: 'base64'});

const url = 'https://developers.typless.com/api/extract-data';

const payload = {
    file: base64File,
    file_name: fileName,
    document_type_name: "vat-invoice"
}

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

let options = {
    method: 'POST',
    headers: headers,
    body: JSON.stringify(payload)
};

fetch(url, options)
    .then(res => res.json())
    .then(json => {
        json.extracted_fields.forEach(field => console.log(`${field.name}: ${field.values[0].value}`))
        console.log('--- VAT RATES ---');
        json.vat_rates.forEach(vatRate => {
            vatRate.forEach(field => {
                console.log(`${field.name}: ${field.values[0].value}`);
            })
            console.log('--------------------');
        })
    })
    .catch(err => console.error('error:' + err));

Response:

{
  "customer": null,
  "extracted_fields": [
    {
      "data_type": "AUTHOR",
      "name": "supplier_name",
      "values": [
        {
          "confidence_score": 0.987,
          "height": -1,
          "page_number": -1,
          "value": "Best flowers Inc.",
          "width": -1,
          "x": -1,
          "y": -1
        }
      ]
    },
    {
      "data_type": "DATE",
      "name": "pay_due_date",
      "values": [
        {
          "confidence_score": 0.99,
          "height": 40,
          "page_number": 0,
          "value": "2017-06-30",
          "width": 481,
          "x": 1818,
          "y": 775
        },
        {
          "confidence_score": 0.125,
          "height": 33,
          "page_number": 0,
          "value": "2017-06-16",
          "width": 608,
          "x": 1685,
          "y": 715
        }
      ]
    },
    {
      "data_type": "STRING",
      "name": "purchase_order_number",
      "values": [
        {
          "confidence_score": 0.99,
          "height": 51,
          "page_number": 0,
          "value": "001-001-35",
          "width": 835,
          "x": 1358,
          "y": 1310
        }
      ]
    },
    {
      "data_type": "NUMBER",
      "name": "total_amount",
      "values": [
        {
          "confidence_score": 0.75,
          "height": 32,
          "page_number": 0,
          "value": "398.3000",
          "width": 112,
          "x": 1208,
          "y": 2978
        },
        {
          "confidence_score": 0.75,
          "height": 33,
          "page_number": 0,
          "value": "61.9500",
          "width": 93,
          "x": 829,
          "y": 2977
        },
        {
          "confidence_score": 0.75,
          "height": 32,
          "page_number": 0,
          "value": "398.3000",
          "width": 112,
          "x": 1208,
          "y": 3048
        },
        {
          "confidence_score": 0.6875,
          "height": 32,
          "page_number": 0,
          "value": "336.3500",
          "width": 114,
          "x": 541,
          "y": 2977
        },
        {
          "confidence_score": 0.625,
          "height": 31,
          "page_number": 0,
          "value": "292.8000",
          "width": 116,
          "x": 1207,
          "y": 2913
        }
      ]
    },
    {
      "data_type": "STRING",
      "name": "invoice_number",
      "values": [
        {
          "confidence_score": 0.99,
          "height": 54,
          "page_number": 0,
          "value": "125/2021",
          "width": 787,
          "x": 1395,
          "y": 1162
        }
      ]
    },
    {
      "data_type": "DATE",
      "name": "issue_date",
      "values": [
        {
          "confidence_score": 0.99,
          "height": 33,
          "page_number": 0,
          "value": "2017-06-16",
          "width": 608,
          "x": 1685,
          "y": 715
        },
        {
          "confidence_score": 0.125,
          "height": 40,
          "page_number": 0,
          "value": "2017-06-30",
          "width": 481,
          "x": 1818,
          "y": 775
        }
      ]
    },
    {
      "data_type": "STRING",
      "name": "receiver_name",
      "values": [
        {
          "confidence_score": 0.99,
          "height": 39,
          "page_number": 0,
          "value": "James Bond",
          "width": 233,
          "x": 170,
          "y": 768
        },
        {
          "confidence_score": 0.3125,
          "height": 32,
          "page_number": 0,
          "value": "losed stre",
          "width": 428,
          "x": 173,
          "y": 816
        },
        {
          "confidence_score": 0.125,
          "height": 51,
          "page_number": 0,
          "value": "chase orde",
          "width": 835,
          "x": 1358,
          "y": 1310
        },
        {
          "confidence_score": 0.125,
          "height": 31,
          "page_number": 0,
          "value": "PIREA GOLD",
          "width": 578,
          "x": 224,
          "y": 1551
        },
        {
          "confidence_score": 0.125,
          "height": 54,
          "page_number": 0,
          "value": "voice numb",
          "width": 787,
          "x": 1395,
          "y": 1162
        }
      ]
    },
    {
      "data_type": "NUMBER",
      "name": "net_amount",
      "values": [
        {
          "confidence_score": 0.5625,
          "height": 32,
          "page_number": 0,
          "value": "336.3500",
          "width": 114,
          "x": 541,
          "y": 2977
        },
        {
          "confidence_score": 0.5,
          "height": 33,
          "page_number": 0,
          "value": "61.9500",
          "width": 93,
          "x": 829,
          "y": 2977
        },
        {
          "confidence_score": 0.5,
          "height": 32,
          "page_number": 0,
          "value": "398.3000",
          "width": 112,
          "x": 1208,
          "y": 2978
        },
        {
          "confidence_score": 0.5,
          "height": 36,
          "page_number": 0,
          "value": "336.3500",
          "width": 219,
          "x": 2093,
          "y": 2068
        },
        {
          "confidence_score": 0.4707,
          "height": 36,
          "page_number": 0,
          "value": "398.3000",
          "width": 242,
          "x": 2063,
          "y": 2217
        }
      ]
    }
  ],
  "file_name": "vat_invoice_2.pdf",
  "line_items": [],
  "object_id": "0d05ad736c837edde4a5aa5434d06da713f7c2b2",
  "vat_rates": [
    [
      {
        "data_type": "NUMBER",
        "name": "vat_rate_percentage",
        "values": [
          {
            "confidence_score": 0.99,
            "height": -1,
            "page_number": -1,
            "value": "9.5000",
            "width": -1,
            "x": -1,
            "y": -1
          }
        ]
      },
      {
        "data_type": "NUMBER",
        "name": "vat_rate_net",
        "values": [
          {
            "confidence_score": 0.99,
            "height": 31,
            "page_number": 0,
            "value": "96.3500",
            "width": 94,
            "x": 561,
            "y": 2838
          }
        ]
      }
    ],
    [
      {
        "data_type": "NUMBER",
        "name": "vat_rate_percentage",
        "values": [
          {
            "confidence_score": 0.99,
            "height": -1,
            "page_number": -1,
            "value": "22.0000",
            "width": -1,
            "x": -1,
            "y": -1
          }
        ]
      },
      {
        "data_type": "NUMBER",
        "name": "vat_rate_net",
        "values": [
          {
            "confidence_score": 0.99,
            "height": 31,
            "page_number": 0,
            "value": "240.0000",
            "width": 116,
            "x": 541,
            "y": 2913
          }
        ]
      }
    ]
  ]
}

You should successfully extract fields along with all the VAT rates present on the invoice.

Need a more in-depth explanation of the response? You can read about it here.

5. Continuously improve models

Typless embraces the fact that the world is changing all the time. That's why you can improve models on the fly by providing correct data after extraction. Let's say your company has a new partner, Best Supplier. You don't need to start over with building the dataset. You can simply extract and send the correct data after they are verified by your users. You can learn more about providing feedback on the building a dataset page.

📘 Closed workflow loop - improve models live!

Use every action from your users to adapt and improve Typless models without any extra costs.

To send feedback, use the add-document-feedback with object_id.

Running Typless live

The only thing that you need to do to automate your manual data entry is to integrate those simple API calls into your system.

Have any questions or need some help? Contact us in chat or send us an email to support@typless.com

PreviousInvoice with line items NextTransport report

Last updated 6 months ago

hashtagOverview

hashtagGetting your API Key

hashtag1. Create a new document type

hashtag2. Add suppliers

hashtag3. Execute training

hashtag4. Extract data from documents

hashtag5. Continuously improve models

hashtagRunning Typless live

Overview

Getting your API Key

1. Create a new document type

2. Add suppliers

3. Execute training

4. Extract data from documents

5. Continuously improve models

Running Typless live