Uncategorized

Consuming an Asset refers to the process of using the Asset to perform a desired action or provide a particular functionality. In this context, it means utilising an Asset to access a trained Document AI model to classify documents and extract information from them.

Once the Asset is created and published, you can send requests to the Asset’s API for processing documents in real time.

Creating a transaction allows you to directly access the published Assets and validate results. This guide will walk you through the steps on how to consume an Asset via the Create Transaction feature. 

Step 1: Select an asset

1. Head to the Asset Monitor module, use the Search bar to find an Asset.
   
   
   
   
2. Select an Asset that you wish to consume.
   
   
   
   

Note: If the Asset is in Inactive status, you must activate the Asset to consume via Create Transaction. For more information about how to activate an Asset, see Activate an Asset page. 

Step 2: Create a transaction

1. On the Overview page that appears, move to the Transaction tab.
   
   
   
   
2. On the Transaction page click Create Transaction and proceed to upload the documents.
   
   
   
   

Step 3: Upload documents

1. In the Create Transaction window that appears, drag and drop the documents (or) Click Browse and select the documents from your local system.  .
   
   

Note:  You can get this window only if the Asset is designed to update the documents at the time of consuming. Otherwise,  you may get different windows based on the Asset. 

2. You can upload the documents based on the following requirements and recommendations:
   • Supported file formats: PDF, PNG, JPEG, TIFF, DOC, DOCX.
   • Maximum document size: 20 MB.
   • Maximum image size: 5 MB.
   • Maximum files allowed: 5 per transaction.
   • Ensure that the file is not password protected and not zipped.
   • Make sure images and documents have a resolution of at least 200 DPI (300 DPI is recommended).
   • Upload documents without watermarks.

Step 4: Stages of the transaction

The transaction contains the following stages for consuming an Asset. You can identify its stages based on the status.

Initiated

This status indicates that your transaction is initiated.

In Progress

This status indicates that the transaction is currently being processed. You may wait for some time to allow the process to complete. If you wish to cancel the transaction, use Suspend Transaction. 

• To suspend a transaction, click and then select Suspend Transaction.
  

In Queue

This status indicates that the transaction is in the queue for review and will take some time to process.

In Review 

This status indicates that the transaction is in the Human in Loop module for manual review. 

Completed

This status indicates that the transaction is completed successfully.

Failed 

This status indicates the transaction has failed due to some reasons. To know the reason, click view reason option against the transaction status.

Suspend

This status indicates the transaction has been cancelled. 

• To suspend a transaction, click and then select Suspend Transaction.
  

Step 5: View the result and download the JSON output

Classifier Asset

1. On the transaction list page, select a transaction.
   
   
   
    
2. On the result page that appears, you can view the transaction result in the JSON output.
   
   
   
   
3. You can also download the JSON file to verify the output sent to the end consuming system.  
4. In the JSON output section, you can identify the following results:
   
   • class: Shows the Document type predicted by the model.
   • conf_score: Shows the confidence score of the model’s prediction.
     
5. In the JSON output section, use to download the JSON file.

Extractor Asset

1. On the transaction list page, select a transaction.
   
   
   
   
2. On the result page that appears, you can view the transaction result in the Extracted fields and JSON output sections.
   
   
   
   

• Extracted Fields section: It shows the fields and the extracted data against those fields. 
  
  
  
  
• JSON section: It shows the result in JSON output.
  
  
  
  

3. In the JSON output section, you can find the following results:
   • label: Shows the label/field name of an entity.
   • text: Shows the data extracted for an entity.
   • text_confidence: This indicates the model’s confidence in its prediction.
   • detection_confidence: This indicates the confidence score associated with the model’s detection.  
4. You can download the JSON file to verify the output sent to the end consuming system. Use to download the JSON format file.

Use case Asset

1. On the transaction list page, select a transaction.
   
   
   
   
2. On the result page that appears, you can view the transaction result in the JSON Output section.
   
   
   
   

3. In the JSON Output section, you can find the following results:
   
   • file_name: Shows the file name of a document.
   • entities: Shows the output results for the entities.
   • value: Shows the data extracted for an entity.
   • conf_score: Indicates the confidence score of the model’s prediction against an entity. 
4. You can also download the JSON file to verify the output sent to the end-consuming system. Use to download the JSON file.

Connectors facilitate easy connection to data sources, allowing you to upload and download the required documents and perform bulk operations.

The platform allows you to configure the Amazon S3 connector. Configuring the  Amazon S3 connector helps you to link your Amazon S3 (a widely used cloud storage service). It enables seamless interaction between the platform and your designated S3 bucket to facilitate efficient document retrieval.

Users must have the Administrator Policy to configure the S3 Connector. 

This guide will walk you through the steps on how to configure the S3 connector.

1. Head to the Administration module, choose Connections and then click Create New.
   
   
   
   
2. In the Select Connector window that appears, select Amazon S3 Connector.
   
   
   

3. On the Amazon S3 Connector page that appears, enter the following details:
   
   
   • In Connection Name, enter a unique and descriptive name for the S3 connector. 
   • In Access_key_Id, enter the Access key. You need to obtain your AWS Access Key from the AWS Management Console. 
   • In Secret_access_key,  enter the Secret Access key. You can retrieve your AWS Secret key from AWS Management Console.
   • In Region, enter the AWS Region where your S3 bucket is located. For more information about AWS regions, see AWS regions.
     

5. Click Submit.
6. Your S3 Connector is successfully configured to connect to the specified AWS S3 bucket using the provided Access Key, Secret Key and Region. Ensure that you have the necessary permissions for the specified S3 bucket and region to avoid connection issues. 

Note: Keep your Access Key and Secret Key secure and do not share them openly. Regularly review and update your connector settings as needed. For more information about the Access key and Secret key, see Amazon Documentation. 

Version: 1.0

Announcement

We are excited to announce the release of the Platform, a powerful AI tool that helps businesses design, deploy, execute and manage document AI models. These models enable business users to contextually extract information from unstructured and semi-structured documents and can be instantly consumed and managed as an API as we refer to as “Assets.” 

The Platform is built on the latest AI and machine learning technologies, and it offers a wide range of capabilities, including:

• Asset Studio: This module allows you to build and manage document AI models, which can be used to extract information from a variety of documents and to automate your document heavy workflows.
• Document Library: This module allows you to store and manage document sets, which can be used to train and test the document AI models.
• Asset Monitor: This module allows you to monitor the performance of the document AI models, and to take action if necessary.
• Human in Loop: This module allows you to review transactions and correct fields that have fallen below the threshold settings.
• Administration: This module allows you to manage users, document types, and connectors.

We are confident that you will find the platform to be a valuable co-pilot for your business to help you to improve the accuracy and efficiency of your document processing processes. We are committed to providing you with the best possible support for the Platform.

Step 1: Create a new document type

1. Head to the Administration module, choose Document Type and select Create New.
   
   
   
   
2. In the Create new Document type page, enter the document type Name.
3. In the Nature of document, select the following required option(s).
   • Free flow – Use this option to extract the information from the documents such as Driving License, Passport, and more. 
   • ID – Use this option to extract the information from the document such as 
   • Form – Use this option to extract the information from the document such as Insurance Application form, Bank Account opening form, and more.

Note: You can select multiple options for the Nature of Document, as some documents may be a combination of Forms, ID cards , and Free flow formats.

4. Optional: Enter a Description and add an Image.
   
   
   
   

Step 2: Add section and group

1. In the Create new Document type page, select Add section.
   
   
   
   
2. The section pane that appears, enter Section header name.
   
   
   
   
3. You can add fields/tables in this section.
   • To add fields in a section, see Define fields in a section.
   • To add tables in a section, see Define tables in a section.

Define fields in a section

1. In the Labels window, select Add field.
   
   
   
   
2. Enter the field name and select the appropriate data type from the drop-down list. 
   
   
   
   
3. You have the option to choose from various data types to annotate and add to your Extractor Asset. Each data type serves a specific purpose and can be tailored to meet your document processing needs.
   • Text: Choose this option if you wish to annotate only textual information against a field. 
   • Number: Choose this option if you wish to annotate numerical values against a field.
   • Datetime: Choose this option if you wish to annotate dates and times against a field.
   • Image: Choose this option if you wish to annotate images against a field. This allows for the extraction and handling of image data within documents.
   • Currency: Choose this option if you wish to annotate currency-related information against a field. 
4. Click Settings against the field and choose any one of the following Expected Label Output options:

Note: Required once option is selected by default.

• Required once: Choose this option if the field is expected only once in the output, regardless of whether it appears and annotated once or multiple times in the document. 
• Required multiple: Choose this option if the field is expected to appear multiple times in the output, depending on whether it appears and annotated once or multiple times in the document.

5. In the Section settings, assign the required following flags to the fields.
   • Header: This label indicates the header of the group. Choose this label to annotate the header for the group of fields. 
   • Start: This label indicates the starting field of the group. Choose this label if you wish to indicate that this field is the start of the group.
   • End: This label indicates the ending field of the group. Choose this label if you wish to indicate that this field is the end of the group.
6. Select the PII check box if the field contains personally identifiable information to encrypt the field value. This option ensures data security of the field’s information. 
7. Select to add additional fields. 
8. Use to delete a field. 

Define tables in a section

1. In the Labels window, select Add table.
   
   
   
   
2. Enter the table name.
3. Click Settings against the table name and choose any one of the following Expected Label Output options:
   • Required once: Choose this option if the field is expected only once in the output, regardless of whether it appears and annotated once or multiple times in the document. 
   • Required multiple: Choose this option if the field is expected to appear multiple times in the output, depending on whether it appears and annotated once or multiple times in the document.
4. Click Add field to define the columns in the table.
   
   
   
   
5. Enter the column name and select the appropriate data type from the drop-down list.
   
   
   
   

6. Select the PII check box if the table contains personally identifiable information to encrypt the table values. This option ensures data security of the field’s information. 
7. Select to add more columns. 
8. Select to add more tables.
9. Select PII check box to encrypt the field value. Use this option for the PII (Personally Identifiable Information). This option ensures data security of the field information.
10. Use to delete a field.

Annotate section and group

This guide will walk you through the steps on how to annotate Section and Group.

Annotate fields and tables

Once you’ve defined the fields and tables within the section, they will appear as shown in the screenshot below. The group’s header is identified by the Header flag , while the starting field of the group is marked with the starting delimiter flag , and the ending field with the ending delimiter flag. However, annotating fields and tables within the section follows a similar process to annotating individual fields and tables.

Annotating fields and tables within the section follows a similar process to annotating individual fields and tables. 
For more information about annotating fields and annotating a table, see Annotate fields and Annotate a table.