DI Analyze (Activity) - Revision history

Rpatton: /* Use in AI-assisted extraction */

2026-06-05T15:53:10Z

Use in AI-assisted extraction

← Older revision		Revision as of 10:53, 5 June 2026
Line 115:		Line 115:

	DI Analyze data is especially useful in AI-assisted extraction workflows.		DI Analyze data is especially useful in AI-assisted extraction workflows.
	When the "Model Name" is set to <code>prebuilt-layout</code>, the saved result can be used with [[~~DI Layout~~]] to inject layout-aware content into AI-powered extraction operations.		When the "Model Name" is set to <code>prebuilt-layout</code>, the saved result can be used with the DI Layout [[Quoting Method]] to inject layout-aware content into AI-powered extraction operations.
	When other prebuilt or custom models are used, the saved JSON result can be referenced through the JSON File quoting method.		When other prebuilt or custom models are used, the saved JSON result can be referenced through the JSON File quoting method.
	This allows extraction steps to work from Azure’s saved analysis output instead of relying only on plain OCR text.		This allows extraction steps to work from Azure’s saved analysis output instead of relying only on plain OCR text.

Rpatton: /* DI Analyze and Azure DI OCR */

2026-06-05T15:52:25Z

DI Analyze and Azure DI OCR

← Older revision		Revision as of 10:52, 5 June 2026
Line 96:		Line 96:
	'''Use DI Analyze Data for Azure DI OCR'''		'''Use DI Analyze Data for Azure DI OCR'''

	However, if you run DI Analyze before running Recognize configured with an Azure DI OCR OCR Profile, Azure DI OCR can use the information obtained by DI Analyze instead of making a second call to Azure Document Intelligence. Keep in mind, that for this to work both DI Analyze and Azure DI OCR need to use the same Model, such as "prebuilt-layout", for Azure DI OCR to use the data from DI Analyze. If DI Analyze is using "prebuilt-layout" but the Azure DI OCR is using "prebuilt-read", then Azure DI OCR will make a second call because you're asking it to get different information using a different Model.		However, if you run DI Analyze before running Recognize configured with an Azure DI OCR OCR Profile, Azure DI OCR can use the information obtained by DI Analyze instead of making a second call to Azure Document Intelligence.

			*<li class="attn-bullet"> Keep in mind, that for this to work both DI Analyze and Azure DI OCR need to use the same Model, such as "prebuilt-layout", for Azure DI OCR to use the data from DI Analyze. If DI Analyze is using "prebuilt-layout" but the Azure DI OCR is using "prebuilt-read", then Azure DI OCR will make a second call because you're asking it to get different information using a different Model.

	== How DI Analyze data is used during extraction ==		== How DI Analyze data is used during extraction ==

Rpatton: // via Wikitext Extension for VSCode

2026-05-27T20:33:14Z

// via Wikitext Extension for VSCode

← Older revision		Revision as of 15:33, 27 May 2026
Line 1:		Line 1:
	~~<%-- [PAGE_INFO]~~
	~~comment = #Please do not remove this struct. It's record contains some important information of edit. This struct will be removed automatically after you push edits.#~~
	~~pageTitle = #DI Analyze#~~
	~~pageID = #10859#~~
	~~revisionID = #32125#~~
	~~contentModel = #wikitext#~~
	~~contentFormat = #text/x-wiki#~~
	~~[END_PAGE_INFO] --%>~~

	{{AutoVersion}}		{{AutoVersion}}

Rpatton: // via Wikitext Extension for VSCode

2026-05-27T15:58:31Z

// via Wikitext Extension for VSCode

← Older revision		Revision as of 10:58, 27 May 2026
Line 1:		Line 1:
			<%-- [PAGE_INFO]
			comment = #Please do not remove this struct. It's record contains some important information of edit. This struct will be removed automatically after you push edits.#
			pageTitle = #DI Analyze#
			pageID = #10859#
			revisionID = #32125#
			contentModel = #wikitext#
			contentFormat = #text/x-wiki#
			[END_PAGE_INFO] --%>

	{{AutoVersion}}		{{AutoVersion}}

Line 84:		Line 93:
	== DI Analyze and Azure DI OCR ==		== DI Analyze and Azure DI OCR ==

	DI Analyze and [[Azure DI OCR]] both use [[Azure Document Intelligence]], but they are designed for different purposes in Grooper.		DI Analyze and Azure DI OCR both use Azure Document Intelligence, but they are designed for different purposes in Grooper.
	* '''DI Analyze''' is a [[Batch Process]] activity that sends a document to Azure Document Intelligence and saves the returned analysis results as a file on the [[Batch Page]] or [[Batch Folder]].		* '''DI Analyze''' is a Batch Process activity that sends a document to Azure Document Intelligence and saves the returned analysis results as a file on the Batch Page or Batch Folder.
	* '''Azure DI OCR''' is an OCR engine used through an [[OCR Profile]] to return OCR results that Grooper can use during OCR processing.		* '''Azure DI OCR''' is an OCR engine used through an [[OCR Profile]] to return OCR results that Grooper can use during OCR processing.

Line 96:		Line 105:
	'''Use DI Analyze Data for Azure DI OCR'''		'''Use DI Analyze Data for Azure DI OCR'''

	However, if you run DI Analyze before running Recognize configured with an Azure DI OCR [[OCR Profile]], Azure DI OCR can use the information obtained by DI Analyze instead of making a second call to Azure Document Intelligence. Keep in mind, that for this to work both DI Analyze and Azure DI OCR need to use the same Model, such as "prebuilt-layout", for Azure DI OCR to use the data from DI Analyze. If DI Analyze is using "prebuilt-layout" but the Azure DI OCR is using "prebuilt-read", then Azure DI OCR will make a second call because you're asking it to get different information using a different Model.		However, if you run DI Analyze before running Recognize configured with an Azure DI OCR OCR Profile, Azure DI OCR can use the information obtained by DI Analyze instead of making a second call to Azure Document Intelligence. Keep in mind, that for this to work both DI Analyze and Azure DI OCR need to use the same Model, such as "prebuilt-layout", for Azure DI OCR to use the data from DI Analyze. If DI Analyze is using "prebuilt-layout" but the Azure DI OCR is using "prebuilt-read", then Azure DI OCR will make a second call because you're asking it to get different information using a different Model.

	== How DI Analyze data is used during extraction ==		== How DI Analyze data is used during extraction ==

	DI Analyze data can be used during extraction as a saved source of Azure Document Intelligence results. Instead of relying only on OCR output at the moment of extraction, later steps in the [[Batch Process]] can reuse the analysis file created by DI Analyze.		DI Analyze data can be used during extraction as a saved source of Azure Document Intelligence results. Instead of relying only on OCR output at the moment of extraction, later steps in the Batch Process can reuse the analysis file created by DI Analyze.

	=== Saved analysis for downstream use ===		=== Saved analysis for downstream use ===

	When DI Analyze runs, it saves the Azure analysis result as a JSON file on the processed [[Batch Page]] or [[Batch Folder]]. This gives downstream extraction steps a stored source of:		When DI Analyze runs, it saves the Azure analysis result as a JSON file on the processed Batch Page or Batch Folder. This gives downstream extraction steps a stored source of:
	* recognized text		* recognized text
	* page layout information		* page layout information
Line 146:		Line 155:

	A common extraction workflow is:		A common extraction workflow is:
	# Run DI Analyze early in the [[Batch Process]].		# Run DI Analyze early in the Batch Process.
	# Save the Azure analysis result to the [[Batch Page]] or [[Batch Folder]].		# Save the Azure analysis result to the Batch Page or Batch Folder.
	# Use the saved result in later for Azure DI OCR, document quoting, AI-assisted extraction, or other downstream extraction steps.		# Use the saved result in later for Azure DI OCR, document quoting, AI-assisted extraction, or other downstream extraction steps.

Line 158:		Line 167:
	=== Configure Azure Document Intelligence (repository option) ===		=== Configure Azure Document Intelligence (repository option) ===

	DI Analyze requires a valid [[Azure Document Intelligence]] configuration.		DI Analyze requires a valid Azure Document Intelligence configuration.

	# To add the Azure Document Intelligence Repository Option, navigate to the Root Node in your node tree.		# To add the Azure Document Intelligence Repository Option, navigate to the Root Node in your node tree.

Rpatton at 15:54, 27 May 2026

2026-05-27T15:54:13Z

← Older revision		Revision as of 10:54, 27 May 2026
Line 1:		Line 1:
	~~<%-- [PAGE_INFO]~~
	~~comment = #Please do not remove this struct. It's record contains some important information of edit. This struct will be removed automatically after you push edits.#~~
	~~pageTitle = #DI Analyze#~~
	~~pageID = #10859#~~
	~~revisionID = #32125#~~
	~~contentModel = #wikitext#~~
	~~contentFormat = #text/x-wiki#~~
	~~[END_PAGE_INFO] --%>~~

	{{AutoVersion}}		{{AutoVersion}}

Rpatton: // via Wikitext Extension for VSCode

2026-05-27T15:53:49Z

// via Wikitext Extension for VSCode

Show changes

Rpatton: Rpatton moved page DI Analyze to DI Analyze (Activity)

2026-05-19T15:06:48Z

Rpatton moved page DI Analyze to DI Analyze (Activity)

← Older revision	Revision as of 10:06, 19 May 2026
(No difference)

Dgreenwood: Created page with "{{NoArticle}}"

2026-01-30T16:57:55Z

Created page with "{{NoArticle}}"

New page