Description:

The Get Text from Document step enables a FlowWright workflow to extract information from a document using Azure Cognitive Services.

The step is part of the Azure Cognitive Services category and is exposed in FlowWright with the display name Get Text from Document. Its XML definition describes the capability as identifying and extracting text, key/value pairs, selection marks, tables, and structure from documents.

The step accepts a document or form path and stores the resulting form text in a workflow variable or global variable. This allows document information to be incorporated into subsequent workflow activities such as validation, data processing, routing, reporting, and database operations.

Typical uses include:

• Extracting text from business documents
• Processing forms automatically
• Extracting key/value information
• Reading tables from documents
• Identifying selection marks
• Processing structured document content
• Automating document intake
• Preparing extracted information for downstream workflow processing

This step enables FlowWright workflows to incorporate document analysis into automated business processes without requiring the document information to be manually entered.

Usage:

The Get Text from Document step is typically used after a workflow receives or generates a document that needs to be analyzed.

During execution:

1. Provide the path to the document or form.
2. Execute the Get Text from Document step.
3. The document is analyzed for its supported content and structure.
4. The extracted form text is stored in the configured workflow variable or global variable.
5. Continue workflow processing through the True or False path.

A typical workflow might look like this:

Typical workflow scenarios include:

• Invoice processing
• Application-form processing
• Purchase-order processing
• Document intake
• Claims processing
• Structured form processing
• Document validation
• Automated data extraction

To use this step, you need to set up an Azure ML service in the FlowWright application. Go to the Status > Settings > Configuration page. Select the Azure ML category from the drop-down menu. Click here to learn more about the Azure ML and Cognitive Service subscription. 

A sample Azure ML configuration is provided here for reference. 

Example:

Let’s build and execute the “clsAzureMLFormRecognizerDef” example. 

• Create a new process definition named “clsAzureMLFormRecognizerDef” and open it in designer mode. 
• Drag a  “clsAzureMLFormRecognizer” step to the canvas.
• Connect the dots between the “Start” and “clsAzureMLFormRecognizer” steps, as shown above. 
• Define a variable or a global variable to store the result.
• Click the "clsAzureMLFormRecognizer" step to configure its "Required" properties. Provide a name for the step. Provide the path to the source document file (supported formats include JPEG, PNG, BMP, PDF, and TIFF). Provide a variable or global reference to store the result. Click the Save button. Note: Click the "AI Predict" button to have Copilot add new process steps that match your process description. 
   

• The “Logging” configuration is necessary for documentation and also measures workflow progress and percent complete. This is achieved by configuring the step state and percent fields individually, as shown in the images below. Configure the “Logging” using the following properties.

• Save the process definition, create a new instance, and run it. Render the process instance. Click the process step to view its properties. The step should retrieve the text from the Form document and store the result in “variable.varResult” as configured. 

Tips:

• Ensure that the configured Form path points to an accessible document before executing the step.
• Store the extracted information in a workflow variable when it is needed by subsequent activities in the current process.
• Use a global variable when the extracted information needs to be referenced more broadly within the workflow.
• Validate extracted information before using it for business-critical decisions.
• Use the False path to handle document-processing failures or unexpected input conditions.
• For structured documents, design downstream processing around the information your particular document types contain.
• Test representative documents before deploying automated extraction workflows into production.

Notes:

• The step belongs to the Azure Cognitive Services category. 
• Its display name is Get Text from document. 
• Form path is required. 
• Variable/Global to store the form text is required. 
• Both inputs are defined as string properties. 
• The step has two input connections and two output connections according to its XML definition. 
• The step provides True and False execution paths. 
• The XML describes extraction of text, key/value pairs, selection marks, tables, and structure, but does not define the detailed runtime schema of the stored result.

Get Text from Document vs. Get Text from Image:

Both Get Text from Document (clsAzureMLFormRecognizer) and Get Text from Image (clsAzureMLGetText) extract information from visual content using Azure Cognitive Services. However, their intended processing scope and configuration are different.

When to use each step:

Use Get Text from Document when the workflow needs to understand a document beyond plain text, such as:

• Forms
• Tables
• Key/value information
• Selection marks
• Document structure
• Structured business documents

Use Get Text from Image when the workflow primarily needs to read text contained within an image, particularly when the text is located in a particular image region or when the workflow needs the additional percentage result defined by that step.

Key distinction:

The simplest way to distinguish the two is:

Get Text from Document: “Analyze this document and extract its text and structural information.”

Get Text from Image: “Read the text contained in this image.”

The Form Recognizer XML explicitly describes the step as identifying and extracting text, key/value pairs, selection marks, tables, and structure from documents.

Definition Sample:

You may download the sample workflow definition from the link provided and import it into your FlowWright environment.

Note: Verify and complete any missing configuration after importing the sample, including:

• Form path
• Variable/Global to store the form text
• Document availability and accessibility
• Success and failure workflow branches
• Downstream processing of the extracted information

After verifying the configuration, save and publish the workflow before execution.

Click here to download the sample file.