2024:Grooper and AI - Revision history

Dgreenwood at 21:47, 27 August 2025

2025-08-27T21:47:53Z

← Older revision		Revision as of 16:47, 27 August 2025
Line 32:		Line 32:
	<big>Major LLM constructs</big>		<big>Major LLM constructs</big>
	* [[LLM Connector]] - A "'''''Repository Option'''''" set on the '''Grooper Root''' node. This provides connectivity to LLMs offered by OpenAI and Microsoft Azure.		* [[LLM Connector]] - A "'''''Repository Option'''''" set on the '''Grooper Root''' node. This provides connectivity to LLMs offered by OpenAI and Microsoft Azure.
	* [[Ask AI]] - An LLM-based '''''Extractor ~~Type~~'''''. This extractor returns results by passing the document's text and a natural language prompt to a chat completion service (a chatbot). The chatbot uses the document's text and the prompt to respond with an answer. The chatbot's answer is the extractor's result.		* [[Ask AI]] - An LLM-based '''''Value Extractor'''''. This extractor returns results by passing the document's text and a natural language prompt to a chat completion service (a chatbot). The chatbot uses the document's text and the prompt to respond with an answer. The chatbot's answer is the extractor's result.
	* [[AI Extract]] - An LLM-based '''''Fill Method'''''. '''''Fill Methods''''' are configured on '''Data Models''' and '''Data Sections'''. They perform a secondary extraction ''after'' the child '''Data Elements''' extractors and extract methods execute. Or, they can act as the primary extraction mechanism if no extractors or extract methods are configured. '''''AI Extract''''' extracts the '''Data Model''' using an LLM chat completion service. In many cases, the only configuration required is '''Data Elements''' added to the model. '''''AI Extract''''' fills in the '''Data Model''' based on what its '''Data Elements''' are named.		* [[AI Extract]] - An LLM-based '''''Fill Method'''''. '''''Fill Methods''''' are configured on '''Data Models''' and '''Data Sections'''. They perform a secondary extraction ''after'' the child '''Data Elements''' extractors and extract methods execute. Or, they can act as the primary extraction mechanism if no extractors or extract methods are configured. '''''AI Extract''''' extracts the '''Data Model''' using an LLM chat completion service. In many cases, the only configuration required is '''Data Elements''' added to the model. '''''AI Extract''''' fills in the '''Data Model''' based on what its '''Data Elements''' are named.
	* [[Clause Detection]] - An LLM-based '''Data Section''' '''''Extract Method'''''. '''''Clause Detection''''' is designed to locate specified types of clauses in natural language documents and return them as section instances in Grooper. The user provides one or more sample clauses, then an embeddings model determines the portion of the document (or "chunk") most similar to the samples, and Grooper returns the paragraph(s) in the chunk. '''Data Sections''' using this '''''Extract Method''''' can then use '''''AI Extract''''' to return data using only the text-content of the detected paragraph.		* [[Clause Detection]] - An LLM-based '''Data Section''' '''''Extract Method'''''. '''''Clause Detection''''' is designed to locate specified types of clauses in natural language documents and return them as section instances in Grooper. The user provides one or more sample clauses, then an embeddings model determines the portion of the document (or "chunk") most similar to the samples, and Grooper returns the paragraph(s) in the chunk. '''Data Sections''' using this '''''Extract Method''''' can then use '''''AI Extract''''' to return data using only the text-content of the detected paragraph.

Dgreenwood at 14:12, 27 August 2025

2025-08-27T14:12:27Z

← Older revision		Revision as of 09:12, 27 August 2025
Line 47:		Line 47:

	[[AI Search]] - This is a larger article covering Grooper's document search and retrieval mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from '''Recognize''') and their extracted data (e.g. '''Data Model''' values collected from '''Extract'''). This article covers the following topics:		[[AI Search]] - This is a larger article covering Grooper's document search and retrieval mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from '''Recognize''') and their extracted data (e.g. '''Data Model''' values collected from '''Extract'''). This article covers the following topics:
	* [[AI Search ~~(Functionality)~~#How To\|How to integrate Grooper with Azure AI Search and set up a new search index]]		* [[AI Search and the Search Page#How To\|How to integrate Grooper with Azure AI Search and set up a new search index]]
	* [[AI Search ~~(Functionality)~~#Index documents and data from Grooper\|The different ways to index documents]]		* [[AI Search and the Search Page#Index documents and data from Grooper\|The different ways to index documents]]
	* [[AI Search ~~(Functionality)~~#Indexing Service\|Set up a Grooper Indexing Service to automatically index documents in the background]]		* [[AI Search and the Search Page#Indexing Service\|Set up a Grooper Indexing Service to automatically index documents in the background]]
	* [[AI Search ~~(Functionality)~~#Search Page\|Navigate and use the Search Page to find documents]]		* [[AI Search and the Search Page#Search Page\|Navigate and use the Search Page to find documents]]
	* [[AI Search ~~(Functionality)~~#Search Page Commands\|Different document and result set commands available from the Search Page]]		* [[AI Search and the Search Page#Search Page Commands\|Different document and result set commands available from the Search Page]]

	== OpenAI and Azure OpenAI Service privacy policies ==		== OpenAI and Azure OpenAI Service privacy policies ==

Dgreenwood: Dgreenwood moved page Grooper and AI to 2024:Grooper and AI

2025-03-05T14:10:49Z

Dgreenwood moved page Grooper and AI to 2024:Grooper and AI

← Older revision	Revision as of 09:10, 5 March 2025
(No difference)

Dgreenwood at 21:37, 28 February 2025

2025-02-28T21:37:57Z

← Older revision		Revision as of 16:37, 28 February 2025
Line 158:		Line 158:
	# Paste the AI Search service's URL in the '''''API Key''''' property.		# Paste the AI Search service's URL in the '''''API Key''''' property.
	# Paste the AI Search service's API key in the '''''API Key''''' property.		# Paste the AI Search service's API key in the '''''API Key''''' property.
	# Full documentation on Grooper's '''''AI Search''''' capabilities can be found in the [[~~Azure~~ AI Search]] article.		# Full documentation on Grooper's '''''AI Search''''' capabilities can be found in the [[AI Search]] article.

	===== External resources =====		===== External resources =====

Dgreenwood at 21:36, 28 February 2025

2025-02-28T21:36:12Z

← Older revision		Revision as of 16:36, 28 February 2025
Line 46:		Line 46:
	=== AI Search ===		=== AI Search ===

	[[~~Azure~~ AI Search]] - This is a larger article covering Grooper's document search and ~~retreival~~ mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from '''Recognize''') and their extracted data (e.g. '''Data Model''' values collected from '''Extract'''). This article covers the following topics:		[[AI Search]] - This is a larger article covering Grooper's document search and retrieval mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from '''Recognize''') and their extracted data (e.g. '''Data Model''' values collected from '''Extract'''). This article covers the following topics:
	* [[AI Search (Functionality)#How To\|How to integrate Grooper with Azure AI Search and set up a new search index]]		* [[AI Search (Functionality)#How To\|How to integrate Grooper with Azure AI Search and set up a new search index]]
	* [[AI Search (Functionality)#Index documents and data from Grooper\|The different ways to index documents]]		* [[AI Search (Functionality)#Index documents and data from Grooper\|The different ways to index documents]]

Dgreenwood: /* OpenAI and Azure OpenAI Service privacy policies */

2025-01-10T17:55:44Z

OpenAI and Azure OpenAI Service privacy policies

← Older revision		Revision as of 12:55, 10 January 2025
Line 53:		Line 53:
	* [[AI Search (Functionality)#Search Page Commands\|Different document and result set commands available from the Search Page]]		* [[AI Search (Functionality)#Search Page Commands\|Different document and result set commands available from the Search Page]]

	=== OpenAI and Azure OpenAI Service privacy policies ===		== OpenAI and Azure OpenAI Service privacy policies ==

	Here, you will find links to OpenAI and Azure OpenAI Service privacy policies.		Here, you will find links to OpenAI and Azure OpenAI Service privacy policies.

Dgreenwood: /* Relevant article links */

2025-01-10T17:55:23Z

Relevant article links

@@ Line 52: / Line 52: @@
 * [[AI Search (Functionality)#Search Page|Navigate and use the Search Page to find documents]]
 * [[AI Search (Functionality)#Search Page Commands|Different document and result set commands available from the Search Page]]
 == OpenAI and Azure account setup ==

Dgreenwood: /* External resources */

2024-12-16T22:43:12Z

External resources

← Older revision		Revision as of 17:43, 16 December 2024
Line 149:		Line 149:
	* [https://learn.microsoft.com/en-us/azure/search/search-create-service-portal Create an AI Search service in the Azure portal]		* [https://learn.microsoft.com/en-us/azure/search/search-create-service-portal Create an AI Search service in the Azure portal]
	* [https://learn.microsoft.com/en-us/azure/search/ Azure AI Search full documentation]		* [https://learn.microsoft.com/en-us/azure/search/ Azure AI Search full documentation]
			* [https://azure.microsoft.com/en-us/pricing/details/search/ Pricing] - Note: Grooper's AI Search integration does not currently use any of the "Premium Features" that incur additional costs beyond the hourly/monthly pricing models.
			* [https://learn.microsoft.com/en-us/azure/search/search-sku-tier How to choose a service tier]
			* [https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity Service limits] - Note: This documents each tier's limits, such as [https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity#index-limits number of indexes], [https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity#partition-storage-gb partition storage], [https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity#vector-index-size-limits vector index storage] and [https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity#document-limits maximum number of documents].

	=== For LLM connectivity ===		=== For LLM connectivity ===

Dgreenwood: /* Azure OCR */

2024-10-30T21:13:29Z

Azure OCR

← Older revision		Revision as of 16:13, 30 October 2024
Line 26:		Line 26:

	=== Azure OCR ===		=== Azure OCR ===
	* [[Azure OCR]] - An '''''OCR Engine''''' option for '''OCR Profiles''' that utilizes Microsoft Azure's Read API. Azure's Read engine is an AI-based text recognition software uses a convolutional neural network (CNN) to recognize text. Compared to traditional OCR engines, it yields superior results especially for handwritten text and poor quality images. Furthermore, Grooper supplements Azure's results with those from a traditional OCR engine in areas where traditional OCR is better than ~~Azure~~.		* [[Azure OCR]] - An '''''OCR Engine''''' option for '''OCR Profiles''' that utilizes Microsoft Azure's Read API. Azure's Read engine is an AI-based text recognition software that uses a convolutional neural network (CNN) to recognize text. Compared to traditional OCR engines, it yields superior results, especially for handwritten text and poor quality images. Furthermore, Grooper supplements Azure's results with those from a traditional OCR engine in areas where traditional OCR is better than the Read engine.

	=== LLM connectivity and constructs ===		=== LLM connectivity and constructs ===

Dgreenwood: /* Relevant article links */

2024-10-30T21:11:04Z

Relevant article links

← Older revision		Revision as of 16:11, 30 October 2024
Line 24:		Line 24:

	Here, you will find links to all currently available articles pertaining to Grooper AI functionality.		Here, you will find links to all currently available articles pertaining to Grooper AI functionality.

			=== Azure OCR ===
			* [[Azure OCR]] - An '''''OCR Engine''''' option for '''OCR Profiles''' that utilizes Microsoft Azure's Read API. Azure's Read engine is an AI-based text recognition software uses a convolutional neural network (CNN) to recognize text. Compared to traditional OCR engines, it yields superior results especially for handwritten text and poor quality images. Furthermore, Grooper supplements Azure's results with those from a traditional OCR engine in areas where traditional OCR is better than Azure.

	=== LLM connectivity and constructs ===		=== LLM connectivity and constructs ===

← Older revision		Revision as of 09:12, 27 August 2025
Line 47:		Line 47:

	[[AI Search]] - This is a larger article covering Grooper's document search and retrieval mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from '''Recognize''') and their extracted data (e.g. '''Data Model''' values collected from '''Extract'''). This article covers the following topics:		[[AI Search]] - This is a larger article covering Grooper's document search and retrieval mechanism. This mechanism uses Microsoft Azure AI Search to index Grooper processed documents for fast and efficient searching. Documents can be searched using their full text content (e.g. OCR from '''Recognize''') and their extracted data (e.g. '''Data Model''' values collected from '''Extract'''). This article covers the following topics:
	* [[AI Search ~~(Functionality)~~#How To\|How to integrate Grooper with Azure AI Search and set up a new search index]]		* [[AI Search and the Search Page#How To\|How to integrate Grooper with Azure AI Search and set up a new search index]]
	* [[AI Search ~~(Functionality)~~#Index documents and data from Grooper\|The different ways to index documents]]		* [[AI Search and the Search Page#Index documents and data from Grooper\|The different ways to index documents]]
	* [[AI Search ~~(Functionality)~~#Indexing Service\|Set up a Grooper Indexing Service to automatically index documents in the background]]		* [[AI Search and the Search Page#Indexing Service\|Set up a Grooper Indexing Service to automatically index documents in the background]]
	* [[AI Search ~~(Functionality)~~#Search Page\|Navigate and use the Search Page to find documents]]		* [[AI Search and the Search Page#Search Page\|Navigate and use the Search Page to find documents]]
	* [[AI Search ~~(Functionality)~~#Search Page Commands\|Different document and result set commands available from the Search Page]]		* [[AI Search and the Search Page#Search Page Commands\|Different document and result set commands available from the Search Page]]

	== OpenAI and Azure OpenAI Service privacy policies ==		== OpenAI and Azure OpenAI Service privacy policies ==