Amazon Textract

Amazon Textract makes it easy to add document text detection and analysis to your RPA applications. Extract structured data from forms and tables in a variety of documents.

Introduction to Amazon Textract Activities Package

Amazon Textract offers a streamlined solution for seamlessly integrating document text detection and analysis into your Robotic Process Automation (RPA) applications. It empowers you to extract structured data from diverse document types, such as invoices, medical records, and tax forms.

Integrating Amazon Textract with UiPath

To facilitate the seamless interaction between UiPath and Amazon Textract, our Amazon Textract activities establish an authenticated connection with your AWS resources through the Amazon Scope activity.

Establishing an Authenticated Connection

Once this connection is established, you gain the ability to incorporate various Amazon Textract activities into both new automation projects and existing ones. To create a secure authenticated connection, our Amazon Textract activities require authorization from the AWS Identity and Access Management (IAM) service.

To enable AWS IAM authorization, you can create or use an existing IAM user and generate access keys (Access Key Id and Secret Access Key). When creating your IAM user, you assign the policies and permissions that specify the resources your Robot can access (e.g., AmazonTextractFullAccess).

Preparing for Project Development

After creating your IAM user and assigning your policies, you enter the Access Key Id and Secret Access Key in the Amazon Scope activity. When you run your automation project, the keys are used to sign the API requests being made by each of the activities.

Before you build your first project, complete the steps in the Setup guide.

After you complete the setup steps, see the Quickstart guides. These guides serve the purpose of assisting you in the creation of functional samples across a spectrum of activities, facilitating both the validation of your connection with the registered app and your familiarity with input/output properties.

Activities in the Amazon Textract Activities Package

The Amazon Textract Activities Package encompasses the following activities:

Amazon Scope

This activity serves as the cornerstone for establishing an authenticated connection between UiPath and your AWS resources, utilizing your IAM credentials.

Analyze Single Page Document

Designed to analyze a local document or a document stored within an S3 bucket, this activity provides detailed document properties in a PageDetail[]  object. These properties can be used as input variables across other activities, extending beyond the Amazon Textract Activities Package.

Analyze Multipage Document

Tailored to analyze multipage documents stored in an S3 bucket, this activity likewise returns document properties in a PageDetail[] object after analysis. These properties can be harnessed as input variables in a range of activities outside the Amazon Textract Activities Package.

Start Document Analysis

Asynchronously starts the analysis of a document stored in an S3 bucket. After starting the document analysis, the activity returns the identifier assigned to the document analysis process as a String (JobId) that you can use as an input variable in the Get Document Analysis Status and Get Document Analysis activities.

Get Document Analysis Status

Asynchronously retrieves the status of an existing or previously executed document analysis job. After retrieving the document analysis, the activity returns the job status as a String value that you can use as a condition to run other activities (e.g. Get Document Analysis).

Get Document Analysis

Asynchronously retrieves the results of a document analysis operation. After retrieving the document analysis, the activity returns the document properties in a PageDetail[] object that you can use as input variables in other activities outside of the Amazon Textract Activities Package.

Applications of the Amazon Textract Activities Package

The Amazon Textract Activities Package can be employed in a variety of use cases where document text detection and analysis are integral to enhancing automation, data extraction, and processing tasks:

• Invoice Processing: Extract key information from invoices, such as invoice numbers, dates, item details, and total amounts.
• Healthcare Record Analysis: Extract patient information, medical diagnoses, treatment plans, billing details from medical records, and enable the automation of medical coding and billing processes, reducing manual data entry and errors.
• Tax Form Analysis: Automate the extraction of data from tax forms, including W-2s, 1099s, and other tax-related documents.