# Projects¶

A Project is the main concept. No data can be shared across projects, only AI models can be shared.

## Create a Project¶

Go to Home and click on the Add button next to Project to create and name a new project.

## Project Details¶

### Name¶

Verbose Name of the Project.

### Decimal Separator¶

Change the decimal separator used to compile the CSV File. Have a look here to see how to change the decimal separator in MS Excel.

### Enable Assignee¶

Will allow assigning users to Documents if enabled.

### Categorization AI¶

Active Categorization AI in the Project.

### Categorization AI Parameters¶

There are advanced configurations for the training of a categorization AI that can be adjusted to achieve a better fitting for your case.

The categorization AI, by default, considers a combination of the text and image features of your documents. Therefore, the categorization of a document will be based on the text of the document and the images of its pages.

However, you can adapt the classifier and choose to only use a text module and, therefore, categorize only based on the text features, for example. The same is possible for only image features.

To do that, you need to pass the dictionary “document_classifier_config” in the “Categorization AI Parameters”. To use only text features, include only the text module. To use only image features, include only the image_module. To use both, include both modules and the multimodal module, that combines them.

{
"document_classifier_config": {
"text_module": {...},
"image_module": {...},
"multimodal_module": {...},
}
}


Furthermore, within each module it is possible to choose the AI architecture and configuration responsible to extract the features.

You change the AI architecture used in the text module by defining its name. The available architectures and respective possible arguments in the text module can be seen here.

For example:

{
"document_classifier_config": {
"text_module": {
"name": "nbow",
"dropout_rate": 0.2,
},
}
}


The same is possible for the image module. The available architectures and respective possible arguments in the image module can be seen here.

For example:

{
"document_classifier_config": {
"image_module": {
"name": "efficientnet_b0",
"freeze": true,
},
}
}


### Project ID¶

ID of the Project used in the REST-API

### Page Limit¶

Maximum Number of Pages per Document.

## Delete a project¶

Go to the List of Projects and select the project you want to delete.

This will delete all data of your project.