> For the complete documentation index, see [llms.txt](https://typless.gitbook.io/typlessapi/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://typless.gitbook.io/typlessapi/automation-use-cases/invoice-with-line-items.md). # Invoice with line items ### Overview This guide covers how to extract metadata and line items from multiple supplier invoices with examples in **Python** and **Node**. For this example, we will use the **Pretrained model**. 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 You will extract the following line item fields: * Product number * Product description * Quantity * Price **This guide shows you how to** 1. [Create invoice-line-items document type](#id-1.-create-a-new-document-type) 2. [Add multiple suppliers](#id-2.-add-suppliers) 3. [Execute training](#id-3.-execute-training) 4. [Extract data from documents](#id-4.-extract-data-from-documents) 5. [Continuously improve models after extraction](#id-5.-continuously-improve-models) ## Getting your API Key The *Authorization* header for your API key is: `Token YOUR-API-KEY` ([Login](https://app.typless.com/login/?redirect=https://docs.typless.com/) if you do not see one).\ You can also obtain the **API key** by visiting the [Settings page](https://app.typless.com/settings/profile). {% embed url="" %} Getting your API key {% endembed %} ## 1. Create a new document type Before you start extracting data, you need to define a document type. Navigate to the [Dashboard page](https://app.typless.com) and click on the **New document type** button in the top right corner of the table. Next, select the **Pretrained model**, followed by **Use a Predefined Template**. Next, click on **Line item invoice** card. The wizard will already pre-fill all the needed [extraction fields](/typlessapi/typless/extraction-fields.md) along with the [document type configuration](/typlessapi/typless/document-type.md).\ Click on the **Create document type**. This will create a new **document type** with name **line-item-invoice** with the following fields: * **`supplier_name`** * **`supplier_vat_id`** * **`buyer_name`** * **`buyer_vat_id`** * **`invoice_number`** * **`payment_reference`** * **`invoice_date`** * **`payment_due_date`** * **`service_date`** * **`total_amount`** * **`net_amount`** * **`vat_amount`** * **`IBAN`** * **`payment_purpose_code`** * **`purchasing_order`** * **`currency`** and line items fields: * **`item_code`** * **`item_description`** * **`unit`** * **`net_amount`** * **`vat_amount`** * **`gross_amount`** * **`discount_percentage`** * **`discount`** * **`unit_price`** * **`quantity`** * **`vat_rate`** ## 2. Extract data from documents {% hint style="success" %} **👍 ****For the Pretrained model, we do not need to train the suppliers - we can start extracting data right away.** {% endhint %} Here are two examples of invoices that you can use for data extraction: * [Amazing Company 2 - download](https://typless-public.s3-eu-west-1.amazonaws.com/use_cases/line-item-invoice/line_items_supplier_1_example_2.pdf) * [Good Services 2 - download](https://typless-public.s3-eu-west-1.amazonaws.com/use_cases/line-item-invoice/line_items_supplier_2_example_2.pdf) Download them and extract the data using the code:
1 Open file as base64 string (Lines 6-7) Make sure that you are pointing to the correct path.
2 Specify payload (Lines 8-12)
3 Specify headers (Lines 16-20)
4 Make POST request (Lines 22-24)
{% tabs %} {% tab title="Python" %} {% code lineNumbers="true" %} ```python import requests import base64 file_name = 'amazing_company_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": "line-item-invoice" } url = "https://developers.typless.com/api/extract-data" headers = { "Accept": "application/json", "Content-Type": "application/json", "Authorization": "<>" } response = requests.request("POST", url, json=payload, headers=headers) for field in response.json()['extracted_fields']: print(f'{field["name"]}: {field["values"][0]["value"]}') ``` {% endcode %} {% endtab %} {% tab title="Node" %} {% code lineNumbers="true" %} ```javascript const fetch = require('node-fetch'); const fs = require('fs'); const fileName = 'amazing_company_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: "line-item-invoice" } const headers = { 'Accept': 'application/json', 'Content-Type': 'application/json', 'Authorization': '<>' } 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}: ${field.values[0].value}`)) json.line_items.forEach( line_item => { console.log('Line item') line_item.forEach(field => console.log(`${field.name}: ${field.values[0].value}`)) } ) } ) .catch(err => console.error('error:' + err)); ``` {% endcode %} {% endtab %} {% endtabs %} **Response:** {% tabs %} {% tab title="JSON" %} {% code lineNumbers="true" %} ```json // Example extraction response - the provided recipe will not produce equal results { "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 } ``` {% endcode %} {% endtab %} {% endtabs %} {% hint style="info" %} **Need a more in-depth explanation of the response?**\ You can read about it [**here**](/typlessapi/typless/data-extraction.md#understanding-response). {% endhint %} ## 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. {% hint style="success" %} **Have any questions or need some help?** Contact us via chat or email **** {% endhint %} ![Typless usage is very easy and straightforward!](https://files.readme.io/ad56c3d-typless_1.PNG)