Conditioning Emails (Simple Functionality) - Revision history

Randallkinard: /* Introduction */

2026-04-17T17:32:17Z

Introduction

← Older revision		Revision as of 12:32, 17 April 2026
Line 11:		Line 11:

	== Introduction ==		== Introduction ==
			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.

	This article is oriented around a "one size fits all" Batch Process designed to condition emails for standard document processing operations in Grooper.		This article is oriented around a "one size fits all" Batch Process designed to condition emails for standard document processing operations in Grooper.

Randallkinard at 20:22, 16 April 2026

2026-04-16T20:22:02Z

@@ Line 1: / Line 1: @@
 == Introduction ==
@@ Line 17: / Line 26: @@
 == Setup for AI Extract ==
-This portion of the article focuses on configuring Grooper’s AI Extract capability so documents can be analyzed by a [https://en.wikipedia.org/wiki/Large_language_model Large Language Model (LLM)] and mapped into a Data Model. It involves setting up an LLM Connector within the [[Repository|Grooper Repository]] and selecting an appropriate model through the Data Model’s [[Fill Method|Fill Methods]].
+This portion of the article focuses on configuring Grooper’s AI Extract capability so documents can be analyzed by a [https://en.wikipedia.org/wiki/Large_language_model Large Language Model (LLM)] and mapped into a [[Data Model]]. It involves setting up an LLM Connector within the [[Repository|Grooper Repository]] and selecting an appropriate model through the Data Model’s [[Fill Method|Fill Methods]].
 The goal of this configuration is to enable Grooper to interpret document content and populate generic fields—such as document identifiers, dates, and party information—without relying on rigid, template-based extraction. This setup establishes the connection between Grooper and the external LLM provider, ensuring AI Extract can execute during Batch Processing.
@@ Line 45: / Line 54: @@
 == Batch Process testing pt.1 ==
-In this section we'll step through a series of Batch Process Steps that highlight the use of the Execute activity and several of its commands.
+In this section we'll step through a series of [[Batch Process Step|Batch Process Steps]] that highlight the use of the [[Execute]] activity and several of its commands.
 # Expand the Node Tree and select the "Expand Email Attachments & Inline Images" Batch Process Step from the provided "Conditioning Emails" Project. Notice The Activity is "Execute", the Scope is "Folder", and the Folder Level is "1".
 # The Execute Command is "Mail Message - Expand Attachments", and Expand Attachments and Expand Inline Images are set to "True". This means it is targeting dot e.m.l. files. If any dot e.m.l. file exists at Folder Level 1 and it has attachments or images embedded in its email body, they'll be expanded.
@@ Line 54: / Line 62: @@
 # Click the "Submit Job" button.
 # In the "Submit Job" window, click the "OK" button.
-# You'll be taken to the Jobs Page. Look for Progress to be "100%" and Status to be "Completed" in the "Processing" properties, then click the "Design Page" button to go back to Design.
+# You'll be taken to the [[Jobs Page]]. Look for Progress to be "100%" and Status to be "Completed" in the "Processing" properties, then click the "[[Design Page]]" button to go back to Design.
 # You'll see the attachments and inline images of the EML files for documents 1 through 4 are expanded and at Folder Level 2.
 # Select the "Expand Email Body (if no attachments)" Batch Process Step. This is an Execute activity with a Scope of "Folder" and a Folder Level of "1".
@@ Line 79: / Line 87: @@
 <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/cmo1wgdev00hlyv0jylde51o9?embed_v=2&utm_source=embed" loading="lazy" title="Conditioning Emails - Batch Process Testing Pt.1" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

Randallkinard at 20:06, 16 April 2026

2026-04-16T20:06:12Z

@@ Line 46: / Line 46: @@
 == Batch Process testing pt.1 ==
 In this section we'll step through a series of Batch Process Steps that highlight the use of the Execute activity and several of its commands.
 <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/cmo1wgdev00hlyv0jylde51o9?embed_v=2&utm_source=embed" loading="lazy" title="Conditioning Emails - Batch Process Testing Pt.1" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

Randallkinard: Created page with " == Introduction == This article is oriented around a "one size fits all" Batch Process designed to condition emails for standard document processing operations in Grooper. Everything in the "Email Conditioning Process" up to "Split Pages" are steps designed to transform documents contained in or attached to an email into usable PDF documents in Grooper. Everything from Split Pages after are fairly typical steps in a Grooper Batch Process (with "Extract Email Data"..."

2026-04-16T20:03:17Z

Created page with " == Introduction == This article is oriented around a "one size fits all" Batch Process designed to condition emails for standard document processing operations in Grooper. Everything in the "Email Conditioning Process" up to "Split Pages" are steps designed to transform documents contained in or attached to an email into usable PDF documents in Grooper. Everything from Split Pages after are fairly typical steps in a Grooper Batch Process (with "Extract Email Data"..."

New page

== Introduction ==
This article is oriented around a "one size fits all" Batch Process designed to condition emails for standard document processing operations in Grooper.

Everything in the "Email Conditioning Process" up to "[[Split Pages]]" are steps designed to transform documents contained in or attached to an email into usable PDF documents in Grooper. Everything from Split Pages after are fairly typical steps in a Grooper Batch Process (with "Extract Email Data" being an exception. This will extract data specifically from the email file itself like the Sender and Subject).

More information on email processing can be found in the Grooper Wiki at:<br>
[[Email Processing]]

The companion Batch in this Project has several examples of common email scenarios:
# When the document is attached to the email.
# When several documents are included in an attached ZIP file.
# When the document is an embedded image in the email's body.
# When the document is the email's body itself.
# (Least common) When the document is a "nested email". When the document is attached to an email that is itself attached to the email.

== Setup for AI Extract ==
This portion of the article focuses on configuring Grooper’s AI Extract capability so documents can be analyzed by a [https://en.wikipedia.org/wiki/Large_language_model Large Language Model (LLM)] and mapped into a Data Model. It involves setting up an LLM Connector within the [[Repository|Grooper Repository]] and selecting an appropriate model through the Data Model’s [[Fill Method|Fill Methods]].

The goal of this configuration is to enable Grooper to interpret document content and populate generic fields—such as document identifiers, dates, and party information—without relying on rigid, template-based extraction. This setup establishes the connection between Grooper and the external LLM provider, ensuring AI Extract can execute during Batch Processing.

# Select the [[Root]] node, then click the ellipsis button for the Options property to open the Options editor.
# Add an LLM Connector, then be sure to properly configure it.
#* The most important configuration is choosing a service provider for the Service Provider property, and properly configuring it.
# Expand the [[Node Tree]] and select the Data Model from the provided "Conditioning Emails" Project, then click the ellipsis button for the Fill Methods property to open the "Fill Methods" editor.
# Expand the Generator sub-properties and be sure to select a desired model for the Model property.

<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/cmo1wg403001vup0ihzewti4k?embed_v=2&utm_source=embed" loading="lazy" title="Conditioning Emails - Setup for AI Extract" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

== Setup for Azure DI OCR ==
This section covers configuring the Azure DI [[OCR Profile]], which is responsible for converting image-based content into machine-readable text. By supplying an Azure Computer Vision API key and matching the correct region, Grooper can leverage Azure DI's OCR engine to process scanned or image-only documents.

This step ensures that all documents—whether they contain embedded text or not—have usable text content for downstream processing. OCR output is critical not only for AI Extract, but also for search indexing, as it provides the textual data that both extraction models and search engines rely on.

# Select the Root node, then click the ellipsis button for the Options property to open the Options editor.
# In the "Options" editor, add an "Azure Document Intelligence" option, then properly configure it.
#* The most important property is the API Key.
# Expand the Node Tree and right-click the "Azure OCR" OCR Profile from the provided "Conditioning Emails" Project, then select "Rename" from the pop-out menu.
# Set the New Name property to "Azure DI OCR".
# Right-click the OCR Engine property, then select "Reset" from the pop-out menu.
# Set the OCR Engine property to "Azure DI OCR".

<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/cmo1wg77t00v1vw0ih89qsixq?embed_v=2&utm_source=embed" loading="lazy" title="Conditioning Emails - Setup for Azure DI OCR" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

== Batch Process testing pt.1 ==
In this section we'll step through a series of Batch Process Steps that highlight the use of the Execute activity and several of its commands.

<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/cmo1wgdev00hlyv0jylde51o9?embed_v=2&utm_source=embed" loading="lazy" title="Conditioning Emails - Batch Process Testing Pt.1" allow="clipboard-write" frameborder="0" webkitallowfullscreen="true" mozallowfullscreen="true" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>