Fine-Tuning for AI Extract - Revision history

Dgreenwood at 20:20, 30 July 2025

2025-07-30T20:20:41Z

← Older revision		Revision as of 15:20, 30 July 2025
Line 8:		Line 8:
	\|		\|
	You may download the ZIP(s) below and upload it into your own Grooper environment (version 2024). The first contains one or more '''Batches''' of sample documents. The second contains one or more '''Projects''' with resources used in examples throughout this article.		You may download the ZIP(s) below and upload it into your own Grooper environment (version 2024). The first contains one or more '''Batches''' of sample documents. The second contains one or more '''Projects''' with resources used in examples throughout this article.
	* [[Media:2025 Wiki - Fine-Tuning Batch.zip]]		* [[Media:2025 Wiki - Fine Tuning Batch.zip]]
	* [[Media:2025 Wiki - Fine-Tuning Project.zip]]		* [[Media:2025 Wiki - Fine Tuning Project.zip]]
	\|}		\|}

Dgreenwood at 20:16, 30 July 2025

2025-07-30T20:16:17Z

← Older revision		Revision as of 15:16, 30 July 2025
Line 2:		Line 2:

	<blockquote>{{#lst:Glossary\|Fine Tuning}}</blockquote>		<blockquote>{{#lst:Glossary\|Fine Tuning}}</blockquote>
	~~<!--~~
	{\|class="download-box"		{\|class="download-box"
	\|		\|
Line 11:		Line 11:
	* [[Media:2025 Wiki - Fine-Tuning Project.zip]]		* [[Media:2025 Wiki - Fine-Tuning Project.zip]]
	\|}		\|}
	~~-->~~

	~~== About ==~~
	Fine-tuning is the process of further training a large language model (LLM) on a specific dataset to make it more specialized for a particular task or domain. This allows the model to adapt its general language understanding to better handle the unique vocabulary, style, and structure of the domain it's fine-tuned on.

	~~In Grooper, you can easily start fine-tuning a model based on a {{DataModelIcon}} [[Data Model]] that will facilitate better extraction when using [[AI Extract]].~~

	=== Info on fine-tuning from OpenAI ===		=== Info on fine-tuning from OpenAI ===

Dgreenwood: /* Delete a fine-tuned model */

2025-07-25T15:51:55Z

Delete a fine-tuned model

← Older revision		Revision as of 10:51, 25 July 2025
Line 115:		Line 115:
	# Open the "Model" editor (Press the "..." button).		# Open the "Model" editor (Press the "..." button).
	# Select the fine-tuned model you want to delete.		# Select the fine-tuned model you want to delete.
	#*<li class="fyi-bullet"> Fine-tuned models created in OpenAI follow this naming convention: <code>ft:{modelName}:{organizationName}:{nameSuffix}:{autoGeneratedId}</code>		#*<li class="fyi-bullet"> Fine-tuned models created in OpenAI follow this naming convention:
			#*:<code>ft:{modelName}:{organizationName}:{nameSuffix}:{autoGeneratedId}</code>
	# Press "OK".		# Press "OK".
	# Press "Execute" to delete the fine-tuned model.		# Press "Execute" to delete the fine-tuned model.

Dgreenwood: /* Delete a fine-tuned model */

2025-07-25T15:51:38Z

Delete a fine-tuned model

← Older revision		Revision as of 10:51, 25 July 2025
Line 108:		Line 108:

	=== Delete a fine-tuned model ===		=== Delete a fine-tuned model ===

			You can delete any fine-tuned models directly from Grooper using the "Delete Fine Tuned Model" command.

			# Right-click any fine-tuning file in Grooper.
			# Select "Fine Tuning > Delete Fine Tuned Model".
			# Open the "Model" editor (Press the "..." button).
			# Select the fine-tuned model you want to delete.
			#*<li class="fyi-bullet"> Fine-tuned models created in OpenAI follow this naming convention: <code>ft:{modelName}:{organizationName}:{nameSuffix}:{autoGeneratedId}</code>
			# Press "OK".
			# Press "Execute" to delete the fine-tuned model.

	== OpenAI API limitations ==		== OpenAI API limitations ==

Dgreenwood: /* Create a fine-tuning file and start a fine-tuning job */

2025-07-25T15:11:26Z

Create a fine-tuning file and start a fine-tuning job

← Older revision		Revision as of 10:11, 25 July 2025
Line 105:		Line 105:
	# Press "Execute".		# Press "Execute".
	# This will submit the fine-tuning file to the OpenAI API (or an OpenAI compatible API) to start a fine-tuning job.		# This will submit the fine-tuning file to the OpenAI API (or an OpenAI compatible API) to start a fine-tuning job.
	#*<li class="fyi-bullet"> It may take a while for the fine-tuning job to complete. There is no way to monitor the fine-tuning job's progress directly from Grooper. However, you can monitor an OpenAI fine-tuning job from the OpenAI API Platform's Fine-tuning page.		#*<li class="fyi-bullet"> It may take a while for the fine-tuning job to complete. There is no way to monitor the fine-tuning job's progress directly from Grooper. However, you can monitor an OpenAI fine-tuning job from the [https://platform.openai.com/finetune/ OpenAI API Platform's Fine-tuning page].

	=== Delete a fine-tuned model ===		=== Delete a fine-tuned model ===

Dgreenwood: /* Create a fine-tuning file and start a fine-tuning job */

2025-07-25T15:10:59Z

Create a fine-tuning file and start a fine-tuning job

← Older revision		Revision as of 10:10, 25 July 2025
Line 105:		Line 105:
	# Press "Execute".		# Press "Execute".
	# This will submit the fine-tuning file to the OpenAI API (or an OpenAI compatible API) to start a fine-tuning job.		# This will submit the fine-tuning file to the OpenAI API (or an OpenAI compatible API) to start a fine-tuning job.
			#*<li class="fyi-bullet"> It may take a while for the fine-tuning job to complete. There is no way to monitor the fine-tuning job's progress directly from Grooper. However, you can monitor an OpenAI fine-tuning job from the OpenAI API Platform's Fine-tuning page.

	=== Delete a fine-tuned model ===		=== Delete a fine-tuned model ===

Dgreenwood: /* Create a fine-tuning file and start a fine-tuning job */

2025-07-25T15:10:01Z

Create a fine-tuning file and start a fine-tuning job

← Older revision		Revision as of 10:10, 25 July 2025
Line 98:		Line 98:

	<big>Start the fine-tuning job</big>		<big>Start the fine-tuning job</big>
			# Locate the fine-tuning file. It is a Resource File in the Data Model's (or Data Section's) parent Content Type's Local Resources Folder.
			# Right-click the fine-tuning file.
			# Select "Fine Tuning > Start Fine Tuning Job".
			# Open the "Base Model" editor and select a base LLM model from the list.
			# Enter a "Name Suffix" of your choosing. This will be appended to the fine-tuned model's name.
			# Press "Execute".
			# This will submit the fine-tuning file to the OpenAI API (or an OpenAI compatible API) to start a fine-tuning job.

	=== Delete a fine-tuned model ===		=== Delete a fine-tuned model ===

Dgreenwood: /* Create a fine-tuning file and start a fine-tuning job */

2025-07-25T14:52:04Z

Create a fine-tuning file and start a fine-tuning job

← Older revision		Revision as of 09:52, 25 July 2025
Line 77:		Line 77:

	=== Create a fine-tuning file and start a fine-tuning job ===		=== Create a fine-tuning file and start a fine-tuning job ===

			<big>Prerequisites</big>
			# Ensure you have an [[LLM Connector]] added to your Grooper Repository.
			# Get one or more Batches ready for fine-tuning.
			#* These should be Batches with ideal data. Any errors in their extracted Data Model should be manually reviewed and corrected.
			#*<li class="attn-bullet"> You must have a minimum of 10 examples to fine-tune a model. Ensure the Batch has at least 10 documents.
			# Ensure you have a Local Resources Folder added to the Data Model's (or Data Section's) parent Content Type.
			#*<li class="attn-bullet"> The fine-tuning file is created as a Resource File that lives in this Local Resources Folder. If the folder does not exist, the "Build Fine Tuning File" command will fail.

			<big>Build the fine-tuning file</big>
			# Right-click the Data Model (or Data Section) where AI Extract is configured.
			# Select "Fine Tuning > Build Fine Tuning File"
			# (Only if necessary) Select the "Fill Method Name".
			#* In most cases, you will not need to configure this property. This will be auto populated with the selected Data Element's Fill Method's name ("AI Extract" unless you changed it).
			#* In rarer cases where multiple Fill Methods are added to a Data Model/Data Section, this dropdown will allow you to choose which one you want to use for fine-tuning.
			# Select one or more Batches for fine-tuning.
			# Press the "Execute" button.
			# A Resource File will be created for the fine-tuning file in the Data Model's (or Data Section's) parent Content Type's Local Resources Folder.
			#*<li class="fyi-bullet"> The fine-tuning file is a JSONL file. Each line in the JSONL file is a separate JSON object, one for each document in the Batch (or Batches). Each JSON object is an example conversation that will be used to better inform a base model how to respond, and thus improve AI Extract's response.

			<big>Start the fine-tuning job</big>

	=== Delete a fine-tuned model ===		=== Delete a fine-tuned model ===

Dgreenwood: /* How To */

2025-07-25T14:18:14Z

How To

← Older revision		Revision as of 09:18, 25 July 2025
Line 75:		Line 75:

	== How To ==		== How To ==

			=== Create a fine-tuning file and start a fine-tuning job ===

			=== Delete a fine-tuned model ===

	== OpenAI API limitations ==		== OpenAI API limitations ==

Dgreenwood: Dgreenwood moved page Fine Tuning (LLM Construct) to Fine-Tuning for AI Extract

2025-07-25T14:14:10Z

Dgreenwood moved page Fine Tuning (LLM Construct) to Fine-Tuning for AI Extract

← Older revision	Revision as of 09:14, 25 July 2025
(No difference)