Glossary - Revision history

Rpatton: /* Misc Properties and Other Configuration Types */

2026-06-08T14:28:36Z

Misc Properties and Other Configuration Types

← Older revision		Revision as of 09:28, 8 June 2026
Line 1,084:		Line 1,084:

	<section begin="DI Layout" />[[DI Layout]] is a Quoting Method that sends Azure Document Intelligence layout results into an AI prompt. Instead of quoting only plain text, it can quote document structure and semantics produced by [[DI Analyze]], such as paragraphs, tables, and page layout. This is useful when the AI needs more than OCR text alone to understand the document.		<section begin="DI Layout" />[[DI Layout]] is a Quoting Method that sends Azure Document Intelligence layout results into an AI prompt. Instead of quoting only plain text, it can quote document structure and semantics produced by [[DI Analyze]], such as paragraphs, tables, and page layout. This is useful when the AI needs more than OCR text alone to understand the document.
	<section end="~~Quoting Method~~" />		<section end="DI Layout" />

	=== Variable Definition ===		=== Variable Definition ===

Rpatton: /* Quoting Method/Document Quoting */

2026-06-08T14:22:47Z

Quoting Method/Document Quoting

← Older revision		Revision as of 09:22, 8 June 2026
Line 1,080:		Line 1,080:
	<section begin="Quoting Method" />[[Quoting Method]]s provide various mechanisms to feed "quotes" from a document to an AI model for Grooper's LLM-based features. Quoting Methods control what text is fed to the AI, allowing users to feed the AI only the necessary context needed to respond or reduce costs by reducing the amount of input tokens sent to the LLM service. Depending on which Quoting Method is selected and configured, the quote may be the entire document text, a portion of a document's text, data extracted from the document, layout data, or a combination of this data.		<section begin="Quoting Method" />[[Quoting Method]]s provide various mechanisms to feed "quotes" from a document to an AI model for Grooper's LLM-based features. Quoting Methods control what text is fed to the AI, allowing users to feed the AI only the necessary context needed to respond or reduce costs by reducing the amount of input tokens sent to the LLM service. Depending on which Quoting Method is selected and configured, the quote may be the entire document text, a portion of a document's text, data extracted from the document, layout data, or a combination of this data.
	*<li class="fyi-bullet"> "Quoting Method" is class of embedded objects that feed quotes to an LLM. Quoting Methods are selected and configured by various items (including [[AI Extract]]) using a "Document Quoting" property.<section end="Quoting Method" />		*<li class="fyi-bullet"> "Quoting Method" is class of embedded objects that feed quotes to an LLM. Quoting Methods are selected and configured by various items (including [[AI Extract]]) using a "Document Quoting" property.<section end="Quoting Method" />

			==== DI Layout ====

			<section begin="DI Layout" />[[DI Layout]] is a Quoting Method that sends Azure Document Intelligence layout results into an AI prompt. Instead of quoting only plain text, it can quote document structure and semantics produced by [[DI Analyze]], such as paragraphs, tables, and page layout. This is useful when the AI needs more than OCR text alone to understand the document.
			<section end="Quoting Method" />

	=== Variable Definition ===		=== Variable Definition ===

Randallkinard: /* AI Assistant */

2026-05-20T13:12:04Z

AI Assistant

← Older revision		Revision as of 08:12, 20 May 2026
Line 31:		Line 31:
	''{{TypeName\|AI Assistant}}''		''{{TypeName\|AI Assistant}}''

	<section begin="AI Assistant" />'''[[AI Assistant]]s''' are Grooper's conversational AI personas. They answer questions about resources it can access (including content from documents, databases and/or web services). This greatly increases an AI's ability to answer domain-specific questions that require access to these resources.<section end="AI Assistant" />		<section begin="AI Assistant" />{{IconName\|Psychology}} '''[[AI Assistant]]s''' are Grooper's conversational AI personas. They answer questions about resources it can access (including content from documents, databases and/or web services). This greatly increases an AI's ability to answer domain-specific questions that require access to these resources.<section end="AI Assistant" />

	=== Batch Objects ===		=== Batch Objects ===

Rpatton: /* DI Analyze */

2026-05-19T15:34:10Z

DI Analyze

← Older revision		Revision as of 10:34, 19 May 2026
Line 414:		Line 414:

	==== DI Analyze ====		==== DI Analyze ====
	<section begin="DI Analyze" />'''DI Analyze''' is a Grooper [[Activity]] (used in a [[Batch Process]]) that submits document content to '''Azure Document Intelligence''' for '''document analysis''' and saves the results back onto the processed item as files. It is designed to capture not only recognized text, but also '''layout and semantic structure''' (for example: lines, words, paragraphs, sections, and other document elements exposed by the selected Azure model).<section end="DI Analyze" />		<section begin="DI Analyze" />{{IconName\|format_image_left}}'''DI Analyze''' is a Grooper [[Activity]] (used in a [[Batch Process]]) that submits document content to '''Azure Document Intelligence''' for '''document analysis''' and saves the results back onto the processed item as files. It is designed to capture not only recognized text, but also '''layout and semantic structure''' (for example: lines, words, paragraphs, sections, and other document elements exposed by the selected Azure model).<section end="DI Analyze" />

	==== Execute ====		==== Execute ====

Rpatton: /* Code Activities */

2026-05-19T15:28:10Z

Code Activities

← Older revision		Revision as of 10:28, 19 May 2026
Line 412:		Line 412:

	<section begin="Detect Language" />{{IconName\|Detect Language}} [[Detect Language]] is an [[Activity]] that uses a large language model (LLM) to determine the primary language (English, Spanish, French, etc.) of a document. Activities executed downstream, such as {{IconName\|Extract}} [[Extract]], can use this information to apply language specific logic.<section end="Detect Language" />		<section begin="Detect Language" />{{IconName\|Detect Language}} [[Detect Language]] is an [[Activity]] that uses a large language model (LLM) to determine the primary language (English, Spanish, French, etc.) of a document. Activities executed downstream, such as {{IconName\|Extract}} [[Extract]], can use this information to apply language specific logic.<section end="Detect Language" />

			==== DI Analyze ====
			<section begin="DI Analyze" />'''DI Analyze''' is a Grooper [[Activity]] (used in a [[Batch Process]]) that submits document content to '''Azure Document Intelligence''' for '''document analysis''' and saves the results back onto the processed item as files. It is designed to capture not only recognized text, but also '''layout and semantic structure''' (for example: lines, words, paragraphs, sections, and other document elements exposed by the selected Azure model).<section end="DI Analyze" />

	==== Execute ====		==== Execute ====

Randallkinard: /* UI Element */

2026-04-21T15:56:02Z

UI Element

← Older revision		Revision as of 10:56, 21 April 2026
Line 1,184:		Line 1,184:
	=== Scan Viewer ===		=== Scan Viewer ===
	<section begin="Scan Viewer" />The [[Scan Viewer]] is a user interface that can be added to the user-attended {{IconName\|person_search}} [[Review]] step in a {{BatchProcessIcon}} '''[[Batch Process]]'''. It is used to scan documents into {{BatchIcon}} '''[[Batch]]es''' from one or more scanning workstations.<section end="Scan Viewer" />		<section begin="Scan Viewer" />The [[Scan Viewer]] is a user interface that can be added to the user-attended {{IconName\|person_search}} [[Review]] step in a {{BatchProcessIcon}} '''[[Batch Process]]'''. It is used to scan documents into {{BatchIcon}} '''[[Batch]]es''' from one or more scanning workstations.<section end="Scan Viewer" />

			=== Stats Page ===
			<section begin="Stats Page" />The [[Stats Page]] in Grooper provides reporting and analytics on system activity, [[Batch Process\|Batch Processing]], and performance metrics. It allows users to track trends, monitor throughput, and evaluate the effectiveness of their Grooper solutions.<section end="Stats Page" />

	=== Summary Tabs ===		=== Summary Tabs ===

Randallkinard: /* Imports Page */

2026-04-17T19:26:28Z

Imports Page

← Older revision		Revision as of 14:26, 17 April 2026
Line 1,168:		Line 1,168:

	=== Imports Page ===		=== Imports Page ===
	<section begin="Imports Page" />The [[Imports Page]] in ~~the~~ Grooper is used to bring documents into the system for processing. It provides a user-friendly interface for uploading files and initiating ingestion into batches.<section end="Imports Page" />		<section begin="Imports Page" />The [[Imports Page]] in Grooper is used to bring documents into the system for processing. It provides a user-friendly interface for uploading files and initiating ingestion into batches.<section end="Imports Page" />

	=== Jobs Page ===		=== Jobs Page ===

Rpatton: /* Data Rule */

2026-04-15T14:31:30Z

Data Rule

← Older revision		Revision as of 09:31, 15 April 2026
Line 180:		Line 180:
	''{{TypeName\|Data Rule}}''		''{{TypeName\|Data Rule}}''

	<section begin="Data Rule" />{{DataRuleIcon}} '''[[Data Rule]]s''' are used to normalize or otherwise prepare data collected in a {{DataModelIcon}} '''[[Data Model]]''' for downstream processes. '''Data Rules''' ~~define data manipulation~~ logic ~~for~~ data extracted from documents ({{BatchFolderIcon}} '''[[Batch Folder]]s''') ~~to ensure data conforms to expected formats or meets certain standards~~.		<section begin="Data Rule" />{{DataRuleIcon}} '''[[Data Rule]]s''' are used to normalize or otherwise prepare data collected in a {{DataModelIcon}} '''[[Data Model]]''' for downstream processes. '''Data Rules''' apply conditional logic to data extracted from documents ({{BatchFolderIcon}} '''[[Batch Folder]]s''').
	* Each '''Data Rule''' executes a "Data Action" which do things like computing a field's value, parse a field into other fields, perform lookups, and more.		* Each '''Data Rule''' executes a "Data Action" which do things like computing a field's value, parse a field into other fields, perform lookups, and more.
	* Data Actions can be conditionally executed based on a '''Data Rule's''' "Trigger" expression.		* Data Actions can be conditionally executed based on a '''Data Rule's''' "Trigger" expression.
	* A hierarchy of '''Data Rules''' can be created to execute multiple Data Actions and perform complex data transformation tasks.		* A hierarchy of '''Data Rules''' can be created to execute multiple Data Actions and perform complex data transformation tasks.
	* '''Data Rules''' can be applied by:		<section end="Data Rule" />
	** The [[Apply Rules]] activity (must be done after data is collected by the [[Extract]] activity)
	** The Extract activity (will run after the '''Data Model''' extraction)
	** The [[Convert Data]] activity when converting document to another '''Document Type'''
	** They can be applied manually in a [[Data Viewer]] with the "Run Rule" command.<section end="Data Rule" />

	=== Extractor Nodes ===		=== Extractor Nodes ===

Randallkinard: /* UI Element */

2026-04-13T15:29:05Z

UI Element

← Older revision		Revision as of 10:29, 13 April 2026
Line 1,173:		Line 1,173:
	=== Imports Page ===		=== Imports Page ===
	<section begin="Imports Page" />The [[Imports Page]] in the Grooper is used to bring documents into the system for processing. It provides a user-friendly interface for uploading files and initiating ingestion into batches.<section end="Imports Page" />		<section begin="Imports Page" />The [[Imports Page]] in the Grooper is used to bring documents into the system for processing. It provides a user-friendly interface for uploading files and initiating ingestion into batches.<section end="Imports Page" />

			=== Jobs Page ===
			<section begin="Jobs Page" />The [[Jobs Page]] in Grooper provides visibility into background processing operations executed by the system. It allows users to monitor the status, progress, and history of jobs such for [[Batch Process\|Batch Processing]] and scheduled tasks.<section end="Jobs Page" />

	=== Node Tree ===		=== Node Tree ===

Randallkinard: /* UI Element */

2026-04-10T15:56:11Z

UI Element

← Older revision		Revision as of 10:56, 10 April 2026
Line 1,170:		Line 1,170:
	=== Document Viewer ===		=== Document Viewer ===
	<section begin="Document Viewer" />The Grooper [[Document Viewer]] is the portal to your documents. It is the UI that allows you to see a {{BatchFolderIcon}} '''[[Batch Folder]]'s''' (or a {{BatchPageIcon}} '''[[Batch Page]]'s''') image, text content, and more.<section end="Document Viewer" />		<section begin="Document Viewer" />The Grooper [[Document Viewer]] is the portal to your documents. It is the UI that allows you to see a {{BatchFolderIcon}} '''[[Batch Folder]]'s''' (or a {{BatchPageIcon}} '''[[Batch Page]]'s''') image, text content, and more.<section end="Document Viewer" />

			=== Imports Page ===
			<section begin="Imports Page" />The [[Imports Page]] in the Grooper is used to bring documents into the system for processing. It provides a user-friendly interface for uploading files and initiating ingestion into batches.<section end="Imports Page" />

	=== Node Tree ===		=== Node Tree ===