Quick start

typless is an AI-powered document extraction platform for automating manual data entry from any document.
With an easy-to-use API, you can extract data with a single call in a matter of seconds.

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 Simple invoice template and click Create document type.
This will create a new document type with name simple-invoice and the following fields:

• supplier_name
• invoice_number
• pay_due_date
• issue_date
• total_amount

2. Get your API key

To use the typless API you need to authorize your requests with an API key.
The Authorization header for your API key is: <<apiKey>> (Login if you do not see one)
To obtain the API key visit the Settings page.

3. Adding a new supplier

typless is a tool for automation. That's why you need to fill the data set and train it first. To automate a new supplier you need to first add its invoices to the data set. Download invoice from Amazing Company:

Amazing company - download.

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

Dataset is created by uploading an original file with the correct value for each field defined inside the document type:

You have just added your first document to your data set!

4. Execute training

To build the model for extraction you need to trigger the training. Go to the Dashboard page, look for the simple-invoice document type in the list, and click on the .

Wait for a few moments for the training to finish. You can refresh the status by clicking on the refresh button in the top left part of the table.
After the training status says Models trained, the model is ready for data extraction.

5. Extract data from documents

After the training is finished, you can start precisely extracting data from documents from trained suppliers. Download another invoice from Amazing Company:

Amazing company - download.

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

Extract the data:

For each of the defined fields, you get an object inside extracted_fields.
Every field has up to 5 best-predicted value blocks with coordinates, recognized value, and confidence score.
The values are always in a string format.

📘

For simple layouts, one invoice in your data set is enough but for more complex ones you may need around 5 from the same supplier

Congratulations!
You just successfully trained and extracted data with typless. You can now use it to automate manual data entry from any of your invoices.