Through the automatic import and export functionality, Retica offers the possibility to manage the transfer of documents efficiently using FTP/FTPS/SFTP protocols.

In practice, it is possible to configure two folders within the customer’s server when using Retica. One of these folders is designated as “Input”, where the customer can insert the documents to be processed. The other folder, called “Output”, is intended to contain the results of the processing carried out by Retica.

By taking advantage of this configuration, the entire process can be automated. The user will only have to insert the documents in the “Input” folder, and select them during the document import process via the “Import via FTP” button. Retica will detect these files, process them and it will be possible to transfer them to the “Output” folder. In the event that the customer requests that their management system automatically reads the data from the “Output” folder, the process will become completely automated. Therefore, the customer will only be responsible for placing the files in the “Input” folder, selecting them from Retica for import, and once the processing is finished, exporting them to the “Output” folder.

Standard Templates:

• Standard templates are pre-configured to accurately extract text, key-value pairs and tables from common documents such as purchase orders, receipts, invoices and more.
• They do not require manual labeling of documents, as they are already optimized to automatically identify the structure of the most common documents.
• They use artificial intelligence to ensure accurate and autonomous identification of documents, therefore it is not possible to manually modify the identified fields. If the results offered are not satisfactory, it is necessary to use custom templates.
• Standard templates include: Purchase Orders, Invoices, Receipts and Generic Documents.
• Standard templates for purchase orders, invoices and receipts extract only the necessary data from the document according to the chosen template. If you need to extract all the data select the template: Generic Document.

Custom Templates:

• Custom templates allow training of artificial intelligence to understand the specific structure of your documents by mapping just five examples.
• They provide the flexibility to improve the accuracy and specificity of your initial output, tailoring it to your unique needs.
• They offer the ability to integrate human input to further refine the model, creating a highly customized and precise solution, and extract only the information you want to read.
• They are ideal for documents that may have a less common or specific structure, allowing you to achieve optimal results in unique situations.

In short, while standard templates are already configured for common documents, custom templates offer a higher level of customization and precision to adapt to your specific needs.

Custom templates should be used when standard templates fail to produce satisfactory results.

Standard templates use predefined labels to extract text from documents, but sometimes they fail to make a correct association between the text and the labels, especially when dealing with documents with complex or unclear structures.

In such situations, it is possible to create a custom model to train artificial intelligence (AI) to read these documents correctly. You can think of the custom model as a container in which you can insert several examples of a document with the same structure but different data. For this document, you can specify where to find the desired information and what name to assign to each label. This step is essential to ensure correct reading by your business management system (ERP) or your customer relationship management (CRM) system.

Once the AI ​​has been trained, to read documents similar to those loaded into the “container” of the custom model, you need to select the menu item “Start Scan” and then choose “custom templates”. In this way, Retica will be able to correctly identify and associate the text of the documents with the labels defined during the training of the custom model.

Thanks to this process, Retica will be able to correctly recognize the texts in the documents you want to process, since it will identify similar and already labeled documents in the container of the selected custom model.

The limits of a custom template cannot be changed, and once they are reached you must create a new custom template.

No, it is not possible to change this parameter. Retica keeps scanned documents for a month and no longer.

No, unused document scans in the current month’s license do not roll over to the next month’s license. Each month, the software license resets the number of available scans, so unused scans do not carry over or roll over to subsequent months. The license renews with a specific number of scans each month and does not take into account unused scans from previous months.

In order to ensure optimal security, constant maintenance and regular updates at scale, we do not provide on-premises implementation of Retica.

The cloud is the most reliable means through which we can offer a highly scalable service with the highest level of security. It is important to note that cloud-based solutions offer security benefits compared to on-premises solutions.

Retica uses AWS servers which are located in Frankfurt.

You can integrate Retica into your business in less than a day.

Retica can recognize multiple languages, including: English, French, German, Italian, Spanish, Portuguese, Dutch, Chinese, Japanese and Korean.

Retica supports printed and handwritten forms, PDFs, and images.

Through the standard model ‘Generic Documents’, Retica is able to recognize most documents that have a common or known structure.

These are some examples of documents: Estimates, Contracts, Curriculum, Technical Sheets, Purchase Vouchers.

Furthermore, the standard model for ‘Generic Documents’ can also be used to extract all texts related to estimates, purchase orders and receipts, since the dedicated standard models filter the relevant texts and extract only the necessary data.