Extract Data with AI Extract (Simple Functionality) - Revision history

Randallkinard: /* Introduction */

2026-05-21T14:35:06Z

Introduction

← Older revision		Revision as of 09:35, 21 May 2026
Line 14:		Line 14:
	This article demonstrates how to use Grooper’s [[AI Extract]] capability to automatically analyze documents and populate a {{IconName\|Data Model}} [[Data Model]] using a Large Language Model (LLM). This article focuses on the core mechanics of AI-based extraction—showing how Grooper combines OCR, {{IconName\|Content Model}} [[Content Model\|Content Models]], Data Models, and an [[LLM Connector]] to collect structured data from unstructured documents.		This article demonstrates how to use Grooper’s [[AI Extract]] capability to automatically analyze documents and populate a {{IconName\|Data Model}} [[Data Model]] using a Large Language Model (LLM). This article focuses on the core mechanics of AI-based extraction—showing how Grooper combines OCR, {{IconName\|Content Model}} [[Content Model\|Content Models]], Data Models, and an [[LLM Connector]] to collect structured data from unstructured documents.

	The intention of this article is to provide a minimal, easy-to-understand example of AI Extract in action. The included “Generic Document” configuration uses broadly applicable fields such as document ID, document date, and party information so it can work with almost any ~~document type~~. The goal is not to model a specific form, but to illustrate how AI Extract interprets document content and fills Data Fields dynamically. Readers are encouraged to modify or replace these generic fields to match their own document requirements.		The intention of this article is to provide a minimal, easy-to-understand example of AI Extract in action. The included “Generic Document” configuration uses broadly applicable fields such as document ID, document date, and party information so it can work with almost any {{IconName\|Document Type}} [[Document Type]]. The goal is not to model a specific form, but to illustrate how AI Extract interprets document content and fills Data Fields dynamically. Readers are encouraged to modify or replace these generic fields to match their own document requirements.

	This guide also demonstrates two execution methods within Grooper:		This guide also demonstrates two execution methods within Grooper:
	* Using {{IconName\|Batch Process Step}} [[Batch Process Step]] Testers from the {{IconName\|Design Page}} [[Design Page]] to observe and validate each stage of processing, including OCR, ~~{{IconName\|~~Document Type~~}} [[Document Type]]~~ assignment, and AI-driven extraction.		* Using {{IconName\|Batch Process Step}} [[Batch Process Step]] Testers from the {{IconName\|Design Page}} [[Design Page]] to observe and validate each stage of processing, including OCR, Document Type assignment, and AI-driven extraction.
	* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.		* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.

Randallkinard: /* Introduction */

2026-05-21T14:33:39Z

Introduction

← Older revision		Revision as of 09:33, 21 May 2026
Line 17:		Line 17:

	This guide also demonstrates two execution methods within Grooper:		This guide also demonstrates two execution methods within Grooper:
	* Using {{IconName\|Batch Process Step}} [[Batch Process Step]] Testers from the Design Page to observe and validate each stage of processing, including OCR, {{IconName\|Document Type}} [[Document Type]] assignment, and AI-driven extraction.		* Using {{IconName\|Batch Process Step}} [[Batch Process Step]] Testers from the {{IconName\|Design Page}} [[Design Page]] to observe and validate each stage of processing, including OCR, {{IconName\|Document Type}} [[Document Type]] assignment, and AI-driven extraction.
	* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.		* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.

Randallkinard: /* Test using Batch Process Step Testers */

2026-05-21T14:33:15Z

Test using Batch Process Step Testers

← Older revision		Revision as of 09:33, 21 May 2026
Line 25:		Line 25:

	== Test using Batch Process Step Testers ==		== Test using Batch Process Step Testers ==
	This portion of the article demonstrates how to execute the "Generic Document Extraction" Batch Process manually from the ~~{{IconName\|~~Design Page~~}} [[Design Page]]~~ using Grooper’s Activity Tester tabs of Batch Process Steps. This approach is intended for development, validation, and learning. It allows you to observe how each processing stage contributes to AI-driven data extraction.		This portion of the article demonstrates how to execute the "Generic Document Extraction" Batch Process manually from the Design Page using Grooper’s Activity Tester tabs of Batch Process Steps. This approach is intended for development, validation, and learning. It allows you to observe how each processing stage contributes to AI-driven data extraction.

	Users create a test {{IconName\|Batch}} [[Batch]], import one or more documents, and then run each activity individually—{{IconName\|Split Pages}} [[Split Pages]], {{IconName\|Recognize}} [[Recognize]], {{IconName\|Extract}} [[Extract]], and {{IconName\|Review}} [[Review]]. This makes it possible to confirm that:		Users create a test {{IconName\|Batch}} [[Batch]], import one or more documents, and then run each activity individually—{{IconName\|Split Pages}} [[Split Pages]], {{IconName\|Recognize}} [[Recognize]], {{IconName\|Extract}} [[Extract]], and {{IconName\|Review}} [[Review]]. This makes it possible to confirm that:

Randallkinard: /* Introduction */

2026-05-21T14:32:55Z

Introduction

← Older revision		Revision as of 09:32, 21 May 2026
Line 17:		Line 17:

	This guide also demonstrates two execution methods within Grooper:		This guide also demonstrates two execution methods within Grooper:
	* Using Batch Process Step Testers from the Design ~~page~~ to observe and validate each stage of processing, including OCR, {{IconName\|Document Type}} [[Document Type]] assignment, and AI-driven extraction.		* Using {{IconName\|Batch Process Step}} [[Batch Process Step]] Testers from the Design Page to observe and validate each stage of processing, including OCR, {{IconName\|Document Type}} [[Document Type]] assignment, and AI-driven extraction.
	* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.		* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.

Randallkinard: /* Test using Batch Process Step Testers */

2026-05-21T14:32:29Z

Test using Batch Process Step Testers

← Older revision		Revision as of 09:32, 21 May 2026
Line 25:		Line 25:

	== Test using Batch Process Step Testers ==		== Test using Batch Process Step Testers ==
	This portion of the article demonstrates how to execute the "Generic Document Extraction" Batch Process manually from the {{IconName\|Design Page}} [[Design Page]] using Grooper’s Activity Tester tabs of ~~{{IconName\|Batch Process Step}} [[Batch Process Step\|~~Batch Process Steps]]. This approach is intended for development, validation, and learning. It allows you to observe how each processing stage contributes to AI-driven data extraction.		This portion of the article demonstrates how to execute the "Generic Document Extraction" Batch Process manually from the {{IconName\|Design Page}} [[Design Page]] using Grooper’s Activity Tester tabs of Batch Process Steps. This approach is intended for development, validation, and learning. It allows you to observe how each processing stage contributes to AI-driven data extraction.

	Users create a test {{IconName\|Batch}} [[Batch]], import one or more documents, and then run each activity individually—{{IconName\|Split Pages}} [[Split Pages]], {{IconName\|Recognize}} [[Recognize]], {{IconName\|Extract}} [[Extract]], and {{IconName\|Review}} [[Review]]. This makes it possible to confirm that:		Users create a test {{IconName\|Batch}} [[Batch]], import one or more documents, and then run each activity individually—{{IconName\|Split Pages}} [[Split Pages]], {{IconName\|Recognize}} [[Recognize]], {{IconName\|Extract}} [[Extract]], and {{IconName\|Review}} [[Review]]. This makes it possible to confirm that:

Randallkinard: /* Test using Batch Process Step Testers */

2026-05-21T14:31:15Z

Test using Batch Process Step Testers

← Older revision		Revision as of 09:31, 21 May 2026
Line 75:		Line 75:
	# In the "Add" dialogue, provide a name for the Batch in the Name property, then click the "Execute" button. Here we've named it "A.I. Extract Test".		# In the "Add" dialogue, provide a name for the Batch in the Name property, then click the "Execute" button. Here we've named it "A.I. Extract Test".
	# Select the newly created Batch from the Node Tree, then click the Viewer tab.		# Select the newly created Batch from the Node Tree, then click the Viewer tab.
	# From an Explorer window, drag the provided PDF onto the root Batch Folder of the Batch.		# From an Explorer window, drag the provided PDF onto the root {{IconName\|Batch Folder}} [[Batch Folder]] of the Batch.
	#* Though a document was provided with this example, you can try to use any document you'd like to test.		#* Though a document was provided with this example, you can try to use any document you'd like to test.
	# Now we will begin to test the Batch Process Steps of our Batch Process to affect the contents of our Batch, starting with "Split Pages".		# Now we will begin to test the Batch Process Steps of our Batch Process to affect the contents of our Batch, starting with "Split Pages".

Randallkinard: /* Test using Batch Process Step Testers */

2026-05-21T14:29:43Z

Test using Batch Process Step Testers

Randallkinard: /* Introduction */

2026-05-21T14:25:46Z

Introduction

← Older revision		Revision as of 09:25, 21 May 2026
Line 12:		Line 12:

	== Introduction ==		== Introduction ==
	This article demonstrates how to use Grooper’s [[AI Extract]] capability to automatically analyze documents and populate a Data Model using a Large Language Model (LLM). This article focuses on the core mechanics of AI-based extraction—showing how Grooper combines OCR, [[Content Model\|Content Models]], ~~[[Data Model\|~~Data Models]], and an [[LLM Connector]] to collect structured data from unstructured documents.		This article demonstrates how to use Grooper’s [[AI Extract]] capability to automatically analyze documents and populate a {{IconName\|Data Model}} [[Data Model]] using a Large Language Model (LLM). This article focuses on the core mechanics of AI-based extraction—showing how Grooper combines OCR, {{IconName\|Content Model}} [[Content Model\|Content Models]], Data Models, and an [[LLM Connector]] to collect structured data from unstructured documents.

	The intention of this article is to provide a minimal, easy-to-understand example of AI Extract in action. The included “Generic Document” configuration uses broadly applicable fields such as document ID, document date, and party information so it can work with almost any document type. The goal is not to model a specific form, but to illustrate how AI Extract interprets document content and fills Data Fields dynamically. Readers are encouraged to modify or replace these generic fields to match their own document requirements.		The intention of this article is to provide a minimal, easy-to-understand example of AI Extract in action. The included “Generic Document” configuration uses broadly applicable fields such as document ID, document date, and party information so it can work with almost any document type. The goal is not to model a specific form, but to illustrate how AI Extract interprets document content and fills Data Fields dynamically. Readers are encouraged to modify or replace these generic fields to match their own document requirements.

	This guide also demonstrates two execution methods within Grooper:		This guide also demonstrates two execution methods within Grooper:
	* Using Batch Process Step Testers from the Design page to observe and validate each stage of processing, including OCR, [[Document Type]] assignment, and AI-driven extraction.		* Using Batch Process Step Testers from the Design page to observe and validate each stage of processing, including OCR, {{IconName\|Document Type}} [[Document Type]] assignment, and AI-driven extraction.
	* Using the "Upload Documents" button on the [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.		* Using the "Upload Documents" button on the {{IconName\|Batches Page}} [[Batches Page]] to experience how the same process runs in a streamlined, production-style workflow.

	By the end of this article, readers will understand how to configure an LLM provider, associate an LLM with a Data Model’s [[Fill Method]], execute AI Extract within a [[Batch Process]], and review the structured data produced by the model. This example serves as a foundational pattern that can be expanded into more advanced AI-powered document processing solutions.		By the end of this article, readers will understand how to configure an LLM provider, associate an LLM with a Data Model’s [[Fill Method]], execute AI Extract within a {{IconName\|Batch Process}} [[Batch Process]], and review the structured data produced by the model. This example serves as a foundational pattern that can be expanded into more advanced AI-powered document processing solutions.

	Please feel free to adjust the contents of the Data Model in a way that suits your chosen document best. You can add or remove any [[Data Element]] within the provided [[Project]] you choose to see different results.		Please feel free to adjust the contents of the Data Model in a way that suits your chosen document best. You can add or remove any [[Data Element]] within the provided {{IconName\|Project}} [[Project]] you choose to see different results.

	== Test using Batch Process Step Testers ==		== Test using Batch Process Step Testers ==

Randallkinard: /* Test with the "Upload Documents" button */

2026-05-21T14:13:02Z

Test with the "Upload Documents" button

← Older revision		Revision as of 09:13, 21 May 2026
Line 124:		Line 124:
	This approach highlights the production experience. It reflects how a deployed AI Extract solution behaves in real-world use: users upload documents, processing runs in the background, and structured data is presented for validation. The complexity of OCR, LLM integration, and Data Model execution is encapsulated within the Batch Process, providing a simple and accessible workflow for end users.		This approach highlights the production experience. It reflects how a deployed AI Extract solution behaves in real-world use: users upload documents, processing runs in the background, and structured data is presented for validation. The complexity of OCR, LLM integration, and Data Model execution is encapsulated within the Batch Process, providing a simple and accessible workflow for end users.

	# First we need to publish our Batch Process. Expand the Node Tree and select the "Generic Document Extraction" Batch Process from the provided Project, then click the "Publish" button to publish this Batch Process to the Processes folder.		# First we need to publish our Batch Process.
			#* Expand the Node Tree and select the "Generic Document Extraction" Batch Process from the provided Project, then click the "Publish" button to publish this Batch Process to the Processes folder.
	# Click the "Execute" button in the "Publish" dialogue.		# Click the "Execute" button in the "Publish" dialogue.
	# A published version of the Batch Process now exists in the Processes folder. This Batch Process will now be available to select for production Batches.		# A published version of the Batch Process now exists in the Processes folder.
	# Next, we'll use the "Upload Documents" button from the Batches Page to create a new Batch and leverage our published Batch Process to automate the processing. Click the "Batches Page" button to go to the Batches Page.		#* This Batch Process will now be available to select for production Batches.
	# Click the "Upload Documents" button in the upper right of the Batches Page. This allows us to quickly create and begin processing a small, ad hoc, Batch.		# Next, we'll use the "Upload Documents" button from the Batches Page to create a new Batch and leverage our published Batch Process to automate the processing.
			#* Click the "Batches Page" button to go to the Batches Page.
			# Click the "Upload Documents" button in the upper right of the Batches Page.
			#* This allows us to quickly create and begin processing a small, ad hoc, Batch.
	# Click the "Choose Files" button in the dialogue that appears.		# Click the "Choose Files" button in the dialogue that appears.
	# Select the provided PDF document from the Explorer window that opens, then click the "Open" button. You may use your own document for this as well.		# Select the provided PDF document from the Explorer window that opens, then click the "Open" button.
			#* You may use your own document for this as well.
	# Set the Process property to the published "Generic Document Extraction" Batch Process, then click the "OK" button.		# Set the Process property to the published "Generic Document Extraction" Batch Process, then click the "OK" button.
	# Select the newly imported Batch. If the Batch started paused, you may need to click the "Resume" button to begin processing.		# Select the newly imported Batch.
			#* If the Batch started paused, you may need to click the "Resume" button to begin processing.
	# On the Jobs tab of the Batch Info Viewer, you will see bars indicating the status of the processing of the Batch Process Steps as the running Activity Processing service completes the Tasks of each Job.		# On the Jobs tab of the Batch Info Viewer, you will see bars indicating the status of the processing of the Batch Process Steps as the running Activity Processing service completes the Tasks of each Job.
	# Once processing is complete, double click the Batch.		# Once processing is complete, double click the Batch.
	# The human attended Review activity will open with the Data Viewer to allow review of the extracted data.If you're happy with what you see, you can click the "Complete Task" button to confirm the collected data and finish the Batch Process.		# The human attended Review activity will open with the Data Viewer to allow review of the extracted data.
			#* If you're happy with what you see, you can click the "Complete Task" button to confirm the collected data and finish the Batch Process.

	<div style="position: relative; box-sizing: content-box; max-height: 80vh; max-height: 80svh; width: 100%; aspect-ratio: 1.78; padding: 40px 0 40px 0;"><iframe src="https://app.supademo.com/embed/cmm3ye0a3000uxp0ivk5t2f7y?embed_v=2&utm_source=embed" loading="lazy" title="Test using "Upload Documents" Button" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>		<div style="position: relative; box-sizing: content-box; max-height: 80vh; max-height: 80svh; width: 100%; aspect-ratio: 1.78; padding: 40px 0 40px 0;"><iframe src="https://app.supademo.com/embed/cmm3ye0a3000uxp0ivk5t2f7y?embed_v=2&utm_source=embed" loading="lazy" title="Test using "Upload Documents" Button" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

Randallkinard: /* Test using Batch Process Step Testers */

2026-05-21T14:11:43Z

Test using Batch Process Step Testers

Show changes

← Older revision		Revision as of 09:29, 21 May 2026
Line 25:		Line 25:

	== Test using Batch Process Step Testers ==		== Test using Batch Process Step Testers ==
	This portion of the article demonstrates how to execute the "Generic Document Extraction" Batch Process manually from the [[Design Page]] using Grooper’s Activity Tester tabs of [[Batch Process Step\|Batch Process Steps]]. This approach is intended for development, validation, and learning. It allows you to observe how each processing stage contributes to AI-driven data extraction.		This portion of the article demonstrates how to execute the "Generic Document Extraction" Batch Process manually from the {{IconName\|Design Page}} [[Design Page]] using Grooper’s Activity Tester tabs of {{IconName\|Batch Process Step}} [[Batch Process Step\|Batch Process Steps]]. This approach is intended for development, validation, and learning. It allows you to observe how each processing stage contributes to AI-driven data extraction.

	Users create a test [[Batch]], import one or more documents, and then run each activity individually—[[Split Pages]], [[Recognize]], [[Extract]], and [[Review]]. This makes it possible to confirm that:		Users create a test {{IconName\|Batch}} [[Batch]], import one or more documents, and then run each activity individually—{{IconName\|Split Pages}} [[Split Pages]], {{IconName\|Recognize}} [[Recognize]], {{IconName\|Extract}} [[Extract]], and {{IconName\|Review}} [[Review]]. This makes it possible to confirm that:
	* Pages are properly separated into [[Batch Page]] nodes.		* Pages are properly separated into {{IconName\|Batch Page}} [[Batch Page]] nodes.
	* Text is successfully collected through native text extraction or OCR (using the configured [[Azure OCR]] Profile).		* Text is successfully collected through native text extraction or OCR (using the configured [[Azure OCR]] Profile).
	* The correct Document Type is assigned.		* The correct Document Type is assigned.
	* AI Extract executes the Data Model’s Fill Method using the selected LLM model.		* AI Extract executes the Data Model’s Fill Method using the selected LLM model.
	* Structured field values are written to the Data Model and can be inspected in the [[Data Viewer]] of the [[Review]] activity.		* Structured field values are written to the Data Model and can be inspected in the [[Data Viewer]] of the Review activity.

	This method emphasizes visibility and diagnostic control. It is especially useful for verifying LLM connectivity, testing prompt behavior, confirming field population logic, and troubleshooting extraction results before publishing the process for broader use.		This method emphasizes visibility and diagnostic control. It is especially useful for verifying LLM connectivity, testing prompt behavior, confirming field population logic, and troubleshooting extraction results before publishing the process for broader use.
Line 54:		Line 54:
	# The provided Project is now added in the Projects folder.		# The provided Project is now added in the Projects folder.
	# Next, let's make sure we have a running [[Activity Processing]] service.		# Next, let's make sure we have a running [[Activity Processing]] service.
	#* Click the [[Machine\|Machines]] folder from the Node Tree.		#* Click the {{IconName\|Machine}} [[Machine\|Machines]] folder from the Node Tree.
	#* Notice there is a running Activity Processing service for this repository.		#* Notice there is a running Activity Processing service for this repository.
	#** This is required if you choose to use the "Submit Job" command moving forward. It will also be required to automate processing in a Batch Process.		#** This is required if you choose to use the "Submit Job" command moving forward. It will also be required to automate processing in a Batch Process.
	#* Please refer to the [[Grooper_Command_Console_(Application)#How_To:_Grooper_services\|"How to: Grooper services"]] section of the [[Grooper Command Console\|"Grooper Command Console"]] article of the Grooper Wiki for more information on installing Grooper Services.		#* Please refer to the [[Grooper_Command_Console_(Application)#How_To:_Grooper_services\|"How to: Grooper services"]] section of the [[Grooper Command Console\|"Grooper Command Console"]] article of the Grooper Wiki for more information on installing Grooper Services.
	# Moving on, we'll now configure the "Azure OCR" [[OCR Profile]] that will be leveraged by the Recognize activity to add electronic text to our document.		# Moving on, we'll now configure the "Azure OCR" {{IconName\|OCR Profile}} [[OCR Profile]] that will be leveraged by the Recognize activity to add electronic text to our document.
	#* Expand the Node Tree and select the "Azure OCR" OCR Profile from the provided Project, then insert your Azure OCR API key into the API Key property.		#* Expand the Node Tree and select the "Azure OCR" OCR Profile from the provided Project, then insert your Azure OCR API key into the API Key property.
	# Next, click the drop-down button to the right of the API Region property and select the appropriate API Region for your API key from the drop-down menu.		# Next, click the drop-down button to the right of the API Region property and select the appropriate API Region for your API key from the drop-down menu.
Line 101:		Line 101:
	#* Recognize selectively performs OCR for image-based content (using the "Azure OCR" OCR Profile in the Project) and native text extraction for encoded text content.		#* Recognize selectively performs OCR for image-based content (using the "Azure OCR" OCR Profile in the Project) and native text extraction for encoded text content.
	# Moving on, we'll now test extraction.		# Moving on, we'll now test extraction.
	#* Select the ~~[[Extract\|~~"Extract"]] Batch Process Step.		#* Select the "Extract" Batch Process Step.
	#* Notice the Default Content Type property is set to the "Generic Document" Document Type.		#* Notice the Default Content Type property is set to the "Generic Document" Document Type.
	# Click the Activity Tester tab.		# Click the Activity Tester tab.