Grooper on Azure Marketplace - Revision history

Dgreenwood: /* Demo Projects and Batches */

2025-09-26T17:55:58Z

Demo Projects and Batches

@@ Line 109: / Line 109: @@
 * '''Use Cases'''
 * '''Miscellaneous Demos'''
 ===Simple Functionality===

Dgreenwood: /* Demo Projects and Batches */

2025-09-26T17:50:07Z

Demo Projects and Batches

← Older revision		Revision as of 12:50, 26 September 2025
Line 106:		Line 106:

	They are organized into three folders:		They are organized into three folders:
	* Simple Functionality		* '''Simple Functionality'''
	* Use Cases		* '''Use Cases'''
	*		* '''Miscellaneous Demos'''

	===Simple Functionality===		===Simple Functionality===
Line 168:		Line 168:
	* [https://www.bisok.com/resources/example-projects/use-cases/lease-processing/sample-leases/Sample-Leases_Image-Based-PDFs.zip Sample Leases - Image-Based PDFs]		* [https://www.bisok.com/resources/example-projects/use-cases/lease-processing/sample-leases/Sample-Leases_Image-Based-PDFs.zip Sample Leases - Image-Based PDFs]
	* [https://www.bisok.com/resources/example-projects/use-cases/transcript-processing/sample-transcripts/Sample-Transcripts_Image-Based-PDFs.zip Sample Transcripts - Image-Based PDFs]		* [https://www.bisok.com/resources/example-projects/use-cases/transcript-processing/sample-transcripts/Sample-Transcripts_Image-Based-PDFs.zip Sample Transcripts - Image-Based PDFs]

			=== Miscellaneous Demos ===

			These are miscellaneous Projects used to demonstrate one or more Grooper features. The Project will contain a “READ ME” resource file with notes and instructions on how to configure nodes. These Projects have accompanying Grooper Batches that can be accessed from the Test branch.

			<big>Travel Expenses</big>

			This Project was mainly created to show off Grooper’s Search Page and Chat Page. Using this Project and the resources it contains, users can process a large number of receipts from a publicly available document set. After running these documents through the Batch Process and adding them to a search index, users can use the Search Page to query the processed documents in Grooper. From the Search Page, users can search the full text of each document and/or query by filtering extracted data values. Users may also build an AI Assistant to ask questions about this document set from the Grooper Chat Page.

			[https://www.bisok.com/resources/example-projects/miscellaneous-demos/travel-expenses/Receipts_2017-2024.zip Receipts document set]

			<big>OSCN Legal Documents</big>

			This Project was created to show off Grooper’s AI Assistant capabilties. The documents used for this demo have already been processed and can be uploaded with the accompanying Grooper Batch ZIP. After creating a search index and adding these documents to the index, users can ask questions about the documents from an AI Assistant by adding a “Search Index” reference. This AI Assistant also demonstrates adding a “Web Service” reference. This Web Service reference uses a RAML definition that describes how to query dockets in the Oklahoma State Courts Network. You can ask the AI Assistant questions and will perform a search for case information using various oscn.net web services.

	== Quick Guides ==		== Quick Guides ==

Dgreenwood: /* Demo Projects and Batches */

2025-09-26T17:46:42Z

Demo Projects and Batches

← Older revision		Revision as of 12:46, 26 September 2025
Line 102:		Line 102:

	== Demo Projects and Batches ==		== Demo Projects and Batches ==

			There are several example Projects and Batches that are already present on the Grooper VM. You can find these Batches and Projects in the Grooper Repository from the Design page.

			They are organized into three folders:
			* Simple Functionality
			* Use Cases
			*

			===Simple Functionality===

			These are Projects that demonstrate one or more Grooper features.

			Each use-case based Project has three different versions. Each is tailored for different ingestion scenarios. There is one Project for:
			* Scanned documents
			* Documents imported from a file system
			* Documents imported from an email source

			Each Project will contain one or more “READ ME” resource files with notes and instructions on how to configure nodes. Some of these Projects will also contain accompanying Grooper Batches in the Test branch that can be used to help test the Project.

			<big> Convert Image Based Documents to a Text Searchable PDF</big>

			This resources in this Project can be used to do something very basic that many Grooper users want to do: (1) Get quality OCR results from a document’s page images and (2) create a text searchable PDF version of the document.

			If you don’t have an image-based PDF or TIF of your own, you can test using the ones we’ve provided below.
			* [https://www.bisok.com/resources/example-projects/simple-functionality/text-searchable-pdf-demo/Image-Based-File-Example.tif Image-Based File Example (TIF)]
			* [https://www.bisok.com/resources/example-projects/simple-functionality/text-searchable-pdf-demo/Image-Based-File-Example.pdf Image-Based File Example (PDF)]

			<big>Extract Data with AI Extract</big>

			This Project shows of Grooper’s AI Extract functionality. AI Extract uses a large language model to extract data without the need for traditional extractor setup in Grooper. The Data Model used in this Project has some generic fields that could be extracted from many different kinds of documents. Supply your own documents to see what the Data Model collects! Then, try adding fields relevant to the document to get what you want from the documents.

			<big>Ingest and Index</big>

			The resources in this Project introduce users to adding documents to a Grooper search index. Once added to an index, users can take advantage of the Search Page, Grooper’s powerful document search and retrieval tool.

			There are three different versions of this Project. Each is tailored for different ingestion scenarios. There is one Project for:
			* Scanned documents
			* Documents imported from a file system
			* Documents imported from an email source

			<big>Conditioning Emails</big>

			Importing documents from an email source is a common starting point in document processing. In Grooper, email files need to be conditioned before they can be further processed, depending on how the document is contained within the email (attached to the email, contained in a ZIP attached to the email, contained in the body, etc.). This Project contains a Batch Process designed to handle numerous different email import scenarios. Use the accompanying Batch to test the steps in the Batch Process to get a better understanding of how Grooper can handle multiple different email scenarios in a single Batch Process.

			<big>Making an AI Assistant from HTTP Import</big>

			AI Assistants are Grooper’s powerful conversational AIs. They can answer domain specific questions by accessing a specified set of knowledge resources. Websites are a wealth of knowledge that can can be added to the AI Assistant’s expertise by importing them into Batches using HTTP Import. This Project introduces you to AI Assistants and HTTP Import by instructing you how to import webpages, processing them as documents in a Grooper Batch, adding them to a search index, and hooking that index up to an AI Assistant.

			=== Use Cases ===

			There are three sets of use-case based Projects used to demonstrate one or more Grooper features. These use cases include:
			* Invoice processing
			* Oil and gas lease processing
			* Student transcript processing

			These Projects use Grooper’s AI-based document processing for data extraction and more.

			Each use-case based Project has three different versions. Each is tailored for different ingestion scenarios. There is one Project for:
			* Scanned documents
			* Documents imported from a file system
			* Documents imported from an email source

			Each Project will contain one or more “READ ME” resource files with notes and instructions on how to configure nodes. These Projects also contain accompanying Grooper Batches in the Test branch that can be used to help test the Project. If you'd like to download the PDFs used in these Batches directly, use the links below.
			* [https://www.bisok.com/resources/example-projects/use-cases/invoice-processing/sample-invoices/Sample-Invoices_Image-Based-PDFs.zip Sample Invoices - Image-Based PDFs]
			* [https://www.bisok.com/resources/example-projects/use-cases/lease-processing/sample-leases/Sample-Leases_Image-Based-PDFs.zip Sample Leases - Image-Based PDFs]
			* [https://www.bisok.com/resources/example-projects/use-cases/transcript-processing/sample-transcripts/Sample-Transcripts_Image-Based-PDFs.zip Sample Transcripts - Image-Based PDFs]

	== Quick Guides ==		== Quick Guides ==

Dgreenwood: /* The Search Page */

2025-09-26T17:28:58Z

The Search Page

← Older revision		Revision as of 12:28, 26 September 2025
Line 96:		Line 96:

	=== The Search Page ===		=== The Search Page ===

			<div style="position: relative; box-sizing: content-box; max-height: 80vh; max-height: 80svh; width: 100%; aspect-ratio: 1.7777777777777777; padding: 40px 0 40px 0;"><iframe src="https://app.supademo.com/embed/cmg0wjd1u0022yx0ii4vr8eys?embed_v=2&utm_source=embed" loading="lazy" title="2025 - Navigating the Grooper UI - The Search Page" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

	=== The Chat Page ===		=== The Chat Page ===

Dgreenwood: /* The Stats Page */

2025-09-25T21:31:17Z

The Stats Page

← Older revision		Revision as of 16:31, 25 September 2025
Line 92:		Line 92:

	=== The Stats Page ===		=== The Stats Page ===

			<div style="position: relative; box-sizing: content-box; max-height: 80vh; max-height: 80svh; width: 100%; aspect-ratio: 1.7777777777777777; padding: 40px 0 40px 0;"><iframe src="https://app.supademo.com/embed/cmfzwqcwq00vk0n0i48omz8ge?embed_v=2&utm_source=embed" loading="lazy" title="2025 - Navigating the Grooper UI - The Stats Page" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

	=== The Search Page ===		=== The Search Page ===

Dgreenwood: /* The Jobs Page */

2025-09-25T20:30:05Z

The Jobs Page

← Older revision		Revision as of 15:30, 25 September 2025
Line 88:		Line 88:

	=== The Jobs Page ===		=== The Jobs Page ===

			<div style="position: relative; box-sizing: content-box; max-height: 80vh; max-height: 80svh; width: 100%; aspect-ratio: 1.7777777777777777; padding: 40px 0 40px 0;"><iframe src="https://app.supademo.com/embed/cmfzroyov00ly0n0iqonmrgom?embed_v=2&utm_source=embed" loading="lazy" title="2025 - Navigating the Grooper UI - The Jobs Page" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

	=== The Stats Page ===		=== The Stats Page ===

Dgreenwood: /* The Imports Page */

2025-09-25T16:53:24Z

The Imports Page

← Older revision		Revision as of 11:53, 25 September 2025
Line 84:		Line 84:

	=== The Imports Page ===		=== The Imports Page ===

			<div style="position: relative; box-sizing: content-box; max-height: 80vh; max-height: 80svh; width: 100%; aspect-ratio: 1.7777777777777777; padding: 40px 0 40px 0;"><iframe src="https://app.supademo.com/embed/cmfzkzm8e00luz30jxpck18w0?embed_v=2&utm_source=embed" loading="lazy" title="2025 - Navigating the Grooper UI - The Imports Page" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

	=== The Jobs Page ===		=== The Jobs Page ===

Dgreenwood: /* Create the search index */

2025-09-25T13:38:05Z

Create the search index

← Older revision		Revision as of 08:38, 25 September 2025
Line 191:		Line 191:
	Big changes to a search index require the index to be recreated. This includes anything that changes the structure of the index, such as adding metadata fields. When this happens you will need to delete the search index (execute the "Search > Delete Index" command), then recreate it (execute the "Search > Create Search Index" command), and reindex all documents (most easily done with the "Search > Submit Indexing Job" command).		Big changes to a search index require the index to be recreated. This includes anything that changes the structure of the index, such as adding metadata fields. When this happens you will need to delete the search index (execute the "Search > Delete Index" command), then recreate it (execute the "Search > Create Search Index" command), and reindex all documents (most easily done with the "Search > Submit Indexing Job" command).
	\|}		\|}

			==== Index documents ====

			'''''Documents will only be indexed if their Content Type is or inherits from the Content Type where the Indexing Behavior is configured.'''''

			There are four ways to index documents:
			* '''One-by-one''': To index a single document, right click the document and execute the "Add to Index" command.
			* '''In a Batch Process''': Add an Execute step with an "Add to Index" command to index documents as part of a Batch Process.
			* '''With the "Submit Indexing Job" command''': This command is executed from the Content Type with the Indexing Behavior. It will analyze Content Types in scope and update the search index with new, changed and removed documents. You can find this command by right-clicking the Content Type.
			* '''With the "Indexing Service"''': This is a Grooper service that runs in the background of your Grooper Repository. It periodically polls the Grooper Repository to determine if the search index needs to be updated. It is installed from [[GCC]].

Dgreenwood: /* Add the AI Search option to the Grooper Repository */

2025-09-24T22:19:00Z

Add the AI Search option to the Grooper Repository

← Older revision		Revision as of 17:19, 24 September 2025
Line 152:		Line 152:
	# 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 [[AI Search]] article.		# Full documentation on Grooper's '''AI Search''' capabilities can be found in the [[AI Search]] article.

			==== Add an Indexing Behavior to a Content Type ====

			After adding the AI Search option to the Grooper Repository, the next step is configuring an Indexing Behavior.

			Indexing Behaviors are added to a Content Type in Grooper (usually a Content Model).
			# Select the Content Type you wish to add the Indexing Behavior to.
			# Select the "Behaviors" property and open its editor (Press the "..." button).
			# Press the Add button ({{IconName\|Add}}) to add a new Behavior.
			# Select "Indexing Behavior" from the dropdown list.
			# With the Indexing Behavior selected, configure its properties as needed. Key properties are detailed below. Visit the [[Indexing Behavior]] article for more information.
			#* "Name" - Grooper will automatically name the search index based on the Content Types name, formatted to Azure's specifications. You can adjust it if you wish.
			#* "Included Elements" - If you want to create metadata fields in the search index using elements from the Content Type's Data Model, select them here.
			#* "Built In Fields" - These are additional metadata fields added to the search index. All are selected by default. However, "Content" should be selected to include the document's full text in the index.
			#* "Vector Search" - Enable this property if you wish to activate semantic (embeddings-based) indexing. This will allow AI Assistants to use natural language searches from the Chat Page.
			#* "Auto Index" - Enable this property when using an [[Indexing Service]] to add new documents to the search index automatically.
			# When finished editing the Indexing Behavior, press "OK".
			# Press "OK" to save changes to the "Behaviors" editor.
			# Press the "Save" button ({{IconName\|Save}}) to save changes to the Content Type.

			==== Create the search index ====

			Once an Indexing Behavior is added, you need to create the search index. To do this, you will execute the "Create Search Index" command.

			To execute the "Create Search Index" command:
			# Right-click the Content Type where the Indexing Behavior is configured.
			# Select "Search" then "Create Search Index".
			# Press the "Execute" button to create the search index.

			Grooper will use the Azure AI Search API to create the search index. The search index lives in Azure, but is entirely accessible in Grooper. You use Grooper to add documents and data to the search index. You use the Grooper Search page to retrieve documents added to the search index.

			{\|class="attn-box"
			\|
			⚠
			\|
			'''''In most cases you will only need to create the search index once. Unless making major changes to the index. Then you will need to delete it, recreate it, and reindex your documents.'''''

			Big changes to a search index require the index to be recreated. This includes anything that changes the structure of the index, such as adding metadata fields. When this happens you will need to delete the search index (execute the "Search > Delete Index" command), then recreate it (execute the "Search > Create Search Index" command), and reindex all documents (most easily done with the "Search > Submit Indexing Job" command).
			\|}

Dgreenwood: /* Add the AI Search option to the Grooper Repository */

2025-09-24T21:22:05Z

Add the AI Search option to the Grooper Repository

← Older revision		Revision as of 16:22, 24 September 2025
Line 143:		Line 143:

	==== Add the AI Search option to the Grooper Repository ====		==== Add the AI Search option to the Grooper Repository ====

			With an Azure AI Search service set up in Azure, you can now connect Grooper to it by adding the Grooper AI Search option to the Grooper Repository.

			# From the Design page, go to the '''Grooper Root''' node.
			# Select the '''Options''' property and open its editor (Press the "..." button).
			# Add the '''AI Search''' option.
			# Paste the AI Search service's URL in the '''URL''' 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 [[AI Search]] article.