Models Overview

Overview of Models

What is a Model?

A Model in the Mindee platform is a configurable and reusable template designed to process documents. In technical terms, a model performs an inference on files uploaded to Mindee.

Various types of models are available, from simple text recognition to data extraction and classification. Models use Optical Character Recognition (OCR) combined with sophisticated data processing techniques.

Models allow you to automate the process of turning unstructured document images into actionable, structured data. They can be tailored to different document types and business needs, ensuring that only the most relevant information is captured for your workflows.

On the Models page, you can view, search, and manage all your document extraction models. Each model is represented as a card showing its name, a preview (if available), and a summary of the main fields it extracts. This makes it easy to organize, access, and deploy models for your document processing tasks.

Each Model contains a dedicated set of tools:

• Configuration: a model is defined by its configuration, that sets the way it should extract data from documents or analyze files. Configuration depends on the model type.

• Settings: overall settings of the model such as processing zone, storage policy, ownership transfer, etc.

Create a Model

From the Mindee Platform main page, click on "Create your document AI model".

From there you can choose the type of model you want to create:

• Extraction Models to extract structured data from documents

• Utility Models to preprocess or analyze documents

Each type of model will have different creation options.

Live Test

Once a model is created you can test it directly on the platform. You can use your own files or choose from our samples selection.

More details in the Live Test section.

Changing Settings

Settings control the high-level options of the model, such as storage duration and processing zone.

All options are detailed in the Model Settings section.