GPT Embeddings (Classify Method) - Revision history

Dgreenwood at 21:42, 27 August 2025

2025-08-27T21:42:58Z

← Older revision		Revision as of 16:42, 27 August 2025
Line 1:		Line 1:
			__NOINDEX__
	{\|class="important-box"		{\|class="important-box"
	\|		\|

Dgreenwood: Dgreenwood moved page GPT Embeddings (Classification Method) to GPT Embeddings (Classify Method)

2025-06-25T15:45:19Z

Dgreenwood moved page GPT Embeddings (Classification Method) to GPT Embeddings (Classify Method)

← Older revision	Revision as of 10:45, 25 June 2025
(No difference)

Dgreenwood at 18:50, 19 June 2025

2025-06-19T18:50:29Z

← Older revision		Revision as of 13:50, 19 June 2025
Line 5:		Line 5:
	'''LEGACY TECHNOLOGY DETECTED!!'''		'''LEGACY TECHNOLOGY DETECTED!!'''

	'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] ~~method is an~~ improved ~~version~~ of this Classify Method.		'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] and [[LLM Classifier]] methods are improved versions of this Classify Method.

	'''''The GPT Embeddings method will be removed from Grooper in version 2025.'''''		'''''The GPT Embeddings method will be removed from Grooper in version 2025.'''''

Dgreenwood at 21:23, 12 May 2025

2025-05-12T21:23:58Z

← Older revision		Revision as of 16:23, 12 May 2025
Line 5:		Line 5:
	'''LEGACY TECHNOLOGY DETECTED!!'''		'''LEGACY TECHNOLOGY DETECTED!!'''

	'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] method is an improved version of this ~~Classification~~ Method.		'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] method is an improved version of this Classify Method.

	'''''The GPT Embeddings method will be removed from Grooper in version 2025.'''''		'''''The GPT Embeddings method will be removed from Grooper in version 2025.'''''

Dgreenwood at 21:30, 4 March 2025

2025-03-04T21:30:24Z

← Older revision		Revision as of 16:30, 4 March 2025
Line 5:		Line 5:
	'''LEGACY TECHNOLOGY DETECTED!!'''		'''LEGACY TECHNOLOGY DETECTED!!'''

	'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] method is an improved version of this Classification Method. The GPT Embeddings method will be removed from Grooper in version 2025.		'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] method is an improved version of this Classification Method.

			'''''The GPT Embeddings method will be removed from Grooper in version 2025.'''''
	\|}		\|}

Dgreenwood at 21:26, 4 March 2025

2025-03-04T21:26:18Z

← Older revision		Revision as of 16:26, 4 March 2025
Line 1:		Line 1:
	{~~{AutoVersion}}~~		{\|class="important-box"
			\|
			'''!!'''
			\|
			'''LEGACY TECHNOLOGY DETECTED!!'''

	~~{{stubs}~~}		'''''GPT Embeddings''''' is now obsolete. The [[Search Classifier]] method is an improved version of this Classification Method. The GPT Embeddings method will be removed from Grooper in version 2025.
			\|}

	<blockquote>{{#lst:Glossary\|GPT Embeddings}}</blockquote>		<blockquote>{{#lst:Glossary\|GPT Embeddings}}</blockquote>

Randallkinard at 19:39, 21 November 2024

2024-11-21T19:39:17Z

← Older revision		Revision as of 14:39, 21 November 2024
Line 26:		Line 26:
	* This model has 8191 maximum input tokens available.		* This model has 8191 maximum input tokens available.
	\|}		\|}

	~~== Glossary ==~~
	~~<u><big>'''Classification Method'''</big></u>: {{#lst:Glossary\|Classification Method}}~~

	~~<u><big>'''Classification'''</big></u>: {{#lst:Glossary\|Classification}}~~

	~~<u><big>'''Classify'''</big></u>: {{#lst:Glossary\|Classify}}~~

	~~<u><big>'''Content Model'''</big></u>: {{#lst:Glossary\|Content Model}}~~

	~~<u><big>'''Document Type'''</big></u>: {{#lst:Glossary\|Document Type}}~~

	~~<u><big>'''GPT Embeddings'''</big></u>: {{#lst:Glossary\|GPT Embeddings}}~~

Randallkinard at 13:52, 10 May 2024

2024-05-10T13:52:16Z

← Older revision		Revision as of 08:52, 10 May 2024
Line 26:		Line 26:
	* This model has 8191 maximum input tokens available.		* This model has 8191 maximum input tokens available.
	\|}		\|}

			== Glossary ==
			<u><big>'''Classification Method'''</big></u>: {{#lst:Glossary\|Classification Method}}

			<u><big>'''Classification'''</big></u>: {{#lst:Glossary\|Classification}}

			<u><big>'''Classify'''</big></u>: {{#lst:Glossary\|Classify}}

			<u><big>'''Content Model'''</big></u>: {{#lst:Glossary\|Content Model}}

			<u><big>'''Document Type'''</big></u>: {{#lst:Glossary\|Document Type}}

			<u><big>'''GPT Embeddings'''</big></u>: {{#lst:Glossary\|GPT Embeddings}}

Randallkinard: Created page with "{{AutoVersion}} {{stubs}}
{{#lst:Glossary|GPT Embeddings}}
'''''GPT Embeddings''''' should be considered a ''BETA'' feature. * This feature was recently added by the development team without a specific use case in mind. * Rather, it was developed in response to ChatGPT's growing popularity. * While it should work in theory, with no specific use case originating the feature, it has not been extensively tested. * As new use cases emerge that are..."

2024-04-30T14:35:32Z

Created page with "{{AutoVersion}} {{stubs}} <blockquote>{{#lst:Glossary|GPT Embeddings}}</blockquote> '''''GPT Embeddings''''' should be considered a ''BETA'' feature. * This feature was recently added by the development team without a specific use case in mind. * Rather, it was developed in response to ChatGPT's growing popularity. * While it should work in theory, with no specific use case originating the feature, it has not been extensively tested. * As new use cases emerge that are..."

New page

{{AutoVersion}}

{{stubs}}

<blockquote>{{#lst:Glossary|GPT Embeddings}}</blockquote>

'''''GPT Embeddings''''' should be considered a ''BETA'' feature.
* This feature was recently added by the development team without a specific use case in mind.
* Rather, it was developed in response to ChatGPT's growing popularity.
* While it should work in theory, with no specific use case originating the feature, it has not been extensively tested.
* As new use cases emerge that are suited for this feature, this section's documentation will be expanded.

An embedding is a vector (list) of numbers. You can determine the difference between embeddings based on the distance between their vectors. A small distance between embeddings suggests they are highly related. A low distance between the embeddings suggests they are less related.

When using '''''GPT Embeddings''''' to classify documents, you will train the '''Content Model''' by giving Grooper example documents for each '''Document Type'''. The GPT model will assign the '''Document Types''' embeddings based on the text content from each trained document. When documents are classified (using the '''''Classify''''' activity), embeddings from the unclassified document are compared to the trained embedding values for each '''Document Type'''. Documents are then assigned the '''Document Type''' with the most similar embeddings.

For more information on embeddings, visit the following OpenAI documentation:
* https://platform.openai.com/docs/guides/embeddings

{|class="attn-box"
|
⚠
|
Please be aware embeddings have a maximum number of input tokens per request. This means there is a cutoff point for longer documents. How many input tokens are available depends on the GPT model you're using.
* OpenAI recommends using the "text-embedding-ada-002" model for embeddings.
* This model has 8191 maximum input tokens available.
|}