LLM Connector (Repository Option) - Revision history

Dgreenwood: /* Azure AI Foundry deployments */

2026-06-30T13:20:12Z

Azure AI Foundry deployments

← Older revision		Revision as of 08:20, 30 June 2026
Line 116:		Line 116:
	#** For more recent embeddings model deployments this will resemble:		#** For more recent embeddings model deployments this will resemble:
	#*** <code><nowiki>https://{resource-name}.openai.azure.com/openai/v1/embeddings</nowiki></code> for OpenAI deployments.		#*** <code><nowiki>https://{resource-name}.openai.azure.com/openai/v1/embeddings</nowiki></code> for OpenAI deployments.
	#*** <code><nowiki>https://{resource-name}.services.ai.azure.com/models/embeddings</nowiki></code> for other deployments. ''Note: This is the unified endpoint for all embeddings models. However, Microsoft's own documentation currently recommends against using it for OpenAI embedding models due to known routing issues. ~~The~~ OpenAI-specific endpoint ~~above~~ is more reliable at this time.''		#*** <code><nowiki>https://{resource-name}.services.ai.azure.com/models/embeddings</nowiki></code> for other deployments. ''Note: This is the unified endpoint for all embeddings models. However, Microsoft's own documentation currently recommends against using it for OpenAI embedding models due to known routing issues. This OpenAI-specific endpoint is more reliable at this time.''
	#** For older embeddings model deployments this may resemble <code><nowiki>https://{deployment-name}.{region}.inference.ml.azure.com/v1/embeddings</nowiki></code> for non-OpenAI deployments		#** For older embeddings model deployments this may resemble <code><nowiki>https://{deployment-name}.{region}.inference.ml.azure.com/v1/embeddings</nowiki></code> for non-OpenAI deployments
	# Set "Authorization" to the method appropriate for the model deployment in Azure.		# Set "Authorization" to the method appropriate for the model deployment in Azure.

Dgreenwood: /* Azure AI Foundry deployments */

2026-06-25T18:28:25Z

Azure AI Foundry deployments

← Older revision		Revision as of 13:28, 25 June 2026
Line 127:		Line 127:
	#:*<li class="fyi-bullet"> When enabled, certain instructions Grooper generates and information handed to a model are sent as "system" messages instead of "user" messages. This helps an LLM distinguish between contextual information and input from a user. This is recommended for most OpenAI models, but may not be supported by all compatible services.		#:*<li class="fyi-bullet"> When enabled, certain instructions Grooper generates and information handed to a model are sent as "system" messages instead of "user" messages. This helps an LLM distinguish between contextual information and input from a user. This is recommended for most OpenAI models, but may not be supported by all compatible services.
	# Press "OK" buttons in each editor to confirm changes and press "Save" on the Grooper Root.		# Press "OK" buttons in each editor to confirm changes and press "Save" on the Grooper Root.
	<section end="azure llm deployment">		<section end="azure llm deployment" />
	<section end="LLM connection options" />		<section end="LLM connection options" />

Dgreenwood: /* Azure AI Foundry deployments */

2026-06-25T18:26:28Z

Azure AI Foundry deployments

← Older revision		Revision as of 13:26, 25 June 2026
Line 106:		Line 106:
	#:*<li class="fyi-bullet"> "Chat Services" are required for most LLM-based features in Grooper, such as AI Extract and AI Assistants. "Embeddings Services" are required when enabling "Vector Search" for an [[Indexing Behavior]], when using the [[Clause Detection]] section extract method, or when using the "Semantic" [[Document Quoting]] method in Grooper.		#:*<li class="fyi-bullet"> "Chat Services" are required for most LLM-based features in Grooper, such as AI Extract and AI Assistants. "Embeddings Services" are required when enabling "Vector Search" for an [[Indexing Behavior]], when using the [[Clause Detection]] section extract method, or when using the "Semantic" [[Document Quoting]] method in Grooper.
	# In the "Model Id" property, enter the deployment's name (Example: "gpt-5").		# In the "Model Id" property, enter the deployment's name (Example: "gpt-5").
	#*<li class="attn-bullet"> The model id is the ''deployment's'' name and '''not''' the model's name. ''These may be the same name ~~as the~~ deployment name defaults to the model's name if the user does not provide a custom name. However, these are two different things in Azure.''		#*<li class="attn-bullet"> The model id is the deployment's name and '''not''' the model's name. ''These may be the same name. The deployment name defaults to the model's name if the user does not provide a custom name. However, these are two different things in Azure.''
	# In the "URL" property, enter the endpoint from Azure AI Foundry (formerly Azure AI Studio).		# In the "URL" property, enter the endpoint from Azure AI Foundry (formerly Azure AI Studio).
	#* '''For Chat Service (chat completions) models:'''		#* '''For Chat Service (chat completions) models:'''

Dgreenwood: /* Azure AI Foundry deployments */

2026-06-25T18:23:32Z

Azure AI Foundry deployments

← Older revision		Revision as of 13:23, 25 June 2026
Line 109:		Line 109:
	# In the "URL" property, enter the endpoint from Azure AI Foundry (formerly Azure AI Studio).		# In the "URL" property, enter the endpoint from Azure AI Foundry (formerly Azure AI Studio).
	#* '''For Chat Service (chat completions) models:'''		#* '''For Chat Service (chat completions) models:'''
	#** ~~For more recent~~ chat completions ~~model~~ deployments~~, this~~ will resemble: <code><nowiki>https://{resource-name}.services.ai.azure.com/openai/v1/chat/completions</nowiki></code>		#** Current chat completions deployments use a unified endpoint for both OpenAI and other models. This will resemble: <code><nowiki>https://{resource-name}.services.ai.azure.com/openai/v1/chat/completions</nowiki></code>
	#** For older chat completions model deployments this may resemble:		#** For older chat completions model deployments this may resemble:
	#*** <code><nowiki>https://{resource-name}.openai.azure.com/openai/deployments/{deployment-name}/chat/completions?api-version={api-version}</nowiki></code> for OpenAI deployments		#*** <code><nowiki>https://{resource-name}.openai.azure.com/openai/deployments/{deployment-name}/chat/completions?api-version={api-version}</nowiki></code> for OpenAI deployments

Dgreenwood: /* Azure AI Foundry deployments */

2026-06-25T18:22:33Z

Azure AI Foundry deployments

← Older revision		Revision as of 13:22, 25 June 2026
Line 86:		Line 86:
	* DeepSeek models		* DeepSeek models
	* xAI's grok models		* xAI's grok models
			* open source models, such as Qwen


Line 94:		Line 95:
	:<li class="fyi-bullet"> When searching for compatible models in Azure's Model Catalog, narrow the "inference tasks" to "embeddings".		:<li class="fyi-bullet"> When searching for compatible models in Azure's Model Catalog, narrow the "inference tasks" to "embeddings".

			<section begin="azure llm deployment" />
	To connect Grooper to an Azure model deployment:		To connect Grooper to an Azure model deployment:
	# Go to the Grooper Root node.		# Go to the Grooper Root node.
Line 104:		Line 105:
	# Add a "Chat Service", "Embeddings Service", or both.		# Add a "Chat Service", "Embeddings Service", or both.
	#:*<li class="fyi-bullet"> "Chat Services" are required for most LLM-based features in Grooper, such as AI Extract and AI Assistants. "Embeddings Services" are required when enabling "Vector Search" for an [[Indexing Behavior]], when using the [[Clause Detection]] section extract method, or when using the "Semantic" [[Document Quoting]] method in Grooper.		#:*<li class="fyi-bullet"> "Chat Services" are required for most LLM-based features in Grooper, such as AI Extract and AI Assistants. "Embeddings Services" are required when enabling "Vector Search" for an [[Indexing Behavior]], when using the [[Clause Detection]] section extract method, or when using the "Semantic" [[Document Quoting]] method in Grooper.
	# In the "Model Id" property, enter the ~~model~~'s name (Example: "gpt-35-~~turbo~~").		# In the "Model Id" property, enter the deployment's name (Example: "gpt-5").
	# In the "URL" property, enter the ~~"Target URI"~~ from Azure		#*<li class="attn-bullet"> The model id is the ''deployment's'' name and '''not''' the model's name. ''These may be the same name as the deployment name defaults to the model's name if the user does not provide a custom name. However, these are two different things in Azure.''
	#:*<~~li class="fyi~~-~~bullet"~~> For ~~Azure OpenAI~~ model deployments this ~~will~~ resemble:		# In the "URL" property, enter the endpoint from Azure AI Foundry (formerly Azure AI Studio).
	#:**<code><nowiki>https://{~~your-~~resource-name}.openai.azure.com/openai/deployments/{~~model~~-id}/chat/completions?api-version={api-version}</nowiki></code> for ~~Chat Service~~ deployments		#* '''For Chat Service (chat completions) models:'''
	#:**<code><nowiki>https://{~~your-resource~~-name}.~~openai~~.azure.com/~~openai~~/~~deployments~~/~~{model-id}/embeddings?api-version={api-version}~~</nowiki></code> for Embeddings ~~Service deployments~~		#** For more recent chat completions model deployments, this will resemble: <code><nowiki>https://{resource-name}.services.ai.azure.com/openai/v1/chat/completions</nowiki></code>
	#:*~~<li class="fyi-bullet">~~ For ~~other models deployed in Azure AI Foundry (formerly Azure AI Studio)~~ this will resemble:		#** For older chat completions model deployments this may resemble:
	#:** <code><nowiki>https://{~~model~~-id}.{~~your~~-~~region~~}.~~models~~.ai.azure.com/v1/~~chat/completions~~</nowiki></code> for ~~Chat Service~~ deployments		#*** <code><nowiki>https://{resource-name}.openai.azure.com/openai/deployments/{deployment-name}/chat/completions?api-version={api-version}</nowiki></code> for OpenAI deployments
	#:** <code><nowiki>https://{~~model~~-id}.{~~your-~~region}.~~models~~.ai.azure.com/v1/embeddings</nowiki></code> for ~~Chat Service~~ deployments		#*** <code><nowiki>https://{deployment-name}.{region}.models.ai.azure.com/v1/chat/completions</nowiki></code> for other chat completions models.
			#* '''For Embeddings models:'''
			#** For more recent embeddings model deployments this will resemble:
			#*** <code><nowiki>https://{resource-name}.openai.azure.com/openai/v1/embeddings</nowiki></code> for OpenAI deployments.
			#*** <code><nowiki>https://{resource-name}.services.ai.azure.com/models/embeddings</nowiki></code> for other deployments. ''Note: This is the unified endpoint for all embeddings models. However, Microsoft's own documentation currently recommends against using it for OpenAI embedding models due to known routing issues. The OpenAI-specific endpoint above is more reliable at this time.''
			#** For older embeddings model deployments this may resemble <code><nowiki>https://{deployment-name}.{region}.inference.ml.azure.com/v1/embeddings</nowiki></code> for non-OpenAI deployments
	# Set "Authorization" to the method appropriate for the model deployment in Azure.		# Set "Authorization" to the method appropriate for the model deployment in Azure.
	#:*<li class="fyi-bullet"> How do I know which method to choose? In Azure, under "Keys and Endpoint", you'll typically see		#:*<li class="fyi-bullet"> How do I know which method to choose? In Azure, under "Keys and Endpoint", you'll typically see
Line 121:		Line 127:
	#:*<li class="fyi-bullet"> When enabled, certain instructions Grooper generates and information handed to a model are sent as "system" messages instead of "user" messages. This helps an LLM distinguish between contextual information and input from a user. This is recommended for most OpenAI models, but may not be supported by all compatible services.		#:*<li class="fyi-bullet"> When enabled, certain instructions Grooper generates and information handed to a model are sent as "system" messages instead of "user" messages. This helps an LLM distinguish between contextual information and input from a user. This is recommended for most OpenAI models, but may not be supported by all compatible services.
	# Press "OK" buttons in each editor to confirm changes and press "Save" on the Grooper Root.		# Press "OK" buttons in each editor to confirm changes and press "Save" on the Grooper Root.
			<section end="azure llm deployment">
	<section end="LLM connection options" />		<section end="LLM connection options" />

Dgreenwood: /* LLM-enabled features */

2026-03-18T21:05:43Z

LLM-enabled features

@@ Line 21: / Line 21: @@
 After an LLM Connector has been added to the Grooper Root, several LLM-enabled features are available in Grooper. This includes:
+{{#lst:Grooper and AI|llm-constructs}}
 ==LLM connection options ==

Dgreenwood: /* About */

2026-03-18T21:03:04Z

About

← Older revision		Revision as of 16:03, 18 March 2026
Line 15:		Line 15:
	**<li class="fyi-bullet"> Compatible APIs must use "chat/completions" and "embeddings" endpoints similar to OpenAI API to interoperate with Grooper's LLM features.		**<li class="fyi-bullet"> Compatible APIs must use "chat/completions" and "embeddings" endpoints similar to OpenAI API to interoperate with Grooper's LLM features.
	* '''Azure''' - This provider connects Grooper to LLMs offered by Microsoft Azure in their "Model Catalog" (including Azure OpenAI models).		* '''Azure''' - This provider connects Grooper to LLMs offered by Microsoft Azure in their "Model Catalog" (including Azure OpenAI models).
	* '''GCS''' - GCS (Grooper Cloud Services) is a prototype ~~services~~ for LLMs offered by and through Grooper directly.		* '''GCS''' - GCS (Grooper Cloud Services) is a prototype service for LLMs offered by and through Grooper directly.
	**<li class="attn-bullet">''This provider is still under development. Users may ignore this provider at this time.''		**<li class="attn-bullet">''This provider is still under development. Users may ignore this provider at this time.''

Dgreenwood at 21:02, 18 March 2026

2026-03-18T21:02:12Z

← Older revision		Revision as of 16:02, 18 March 2026
Line 16:		Line 16:
	* '''Azure''' - This provider connects Grooper to LLMs offered by Microsoft Azure in their "Model Catalog" (including Azure OpenAI models).		* '''Azure''' - This provider connects Grooper to LLMs offered by Microsoft Azure in their "Model Catalog" (including Azure OpenAI models).
	* '''GCS''' - GCS (Grooper Cloud Services) is a prototype services for LLMs offered by and through Grooper directly.		* '''GCS''' - GCS (Grooper Cloud Services) is a prototype services for LLMs offered by and through Grooper directly.
	**<li class="attn-bullet">''This provider is still under development. ~~Most users~~ may ignore this provider at this time.''		**<li class="attn-bullet">''This provider is still under development. Users may ignore this provider at this time.''

	== LLM-enabled features ==		== LLM-enabled features ==

Dgreenwood: /* About */

2025-11-13T15:42:49Z

About

@@ Line 17: / Line 17: @@
 * '''GCS''' - GCS (Grooper Cloud Services) is a prototype services for LLMs offered by and through Grooper directly.
 **<li class="attn-bullet">''This provider is still under development. Most users may ignore this provider at this time.''
 ==LLM connection options ==

Dgreenwood: /* OpenAI compatible services */

2025-09-29T18:54:41Z

OpenAI compatible services

← Older revision		Revision as of 13:54, 29 September 2025
Line 43:		Line 43:
	==== OpenAI compatible services ====		==== OpenAI compatible services ====

	Grooper can connect to any LLM service that adheres to the OpenAI API standard using the "OpenAI" provider. Compatible APIs must use "chat/completions" and "embeddings" endpoints ~~similar to~~ OpenAI API to interoperate with Grooper's LLM features.		Grooper can connect to any LLM service that adheres to the OpenAI API standard using the "OpenAI" provider. Compatible APIs must use "chat/completions" and "embeddings" endpoints like OpenAI API to interoperate with Grooper's LLM features.

	We have confirmed the following services will integrate using the OpenAI provider:		We have confirmed the following services will integrate using the OpenAI provider: