Lingoport Wiki - Recent changes [en]

LLM

Olibouban — Wed, 10 Jun 2026 19:23:08 GMT

Example of LLM Types and Models

← Older revision		Revision as of 19:23, 10 June 2026
(One intermediate revision by the same user not shown)
Line 22:		Line 22:
	\| '''Fireworks (OpenAI)''' \|\| <code>https://api.fireworks.ai/inference/v1/chat/completions</code> \|\| accounts/fireworks/models/llama-v3p3-70b-instruct, accounts/fireworks/models/deepseek-v3		\| '''Fireworks (OpenAI)''' \|\| <code>https://api.fireworks.ai/inference/v1/chat/completions</code> \|\| accounts/fireworks/models/llama-v3p3-70b-instruct, accounts/fireworks/models/deepseek-v3
	\|-		\|-
	\| '''Gemini (Gemini)''' \|\| <code>https://generativelanguage.googleapis.com/v1beta/models/</code> \|\| gemini-3.1-pro, gemini-3.5-flash, gemini-2.5-flash-lite		\| '''Gemini (Gemini)''' \|\| <code>https://generativelanguage.googleapis.com/v1beta/models</code> \|\| gemini-3.1-pro, gemini-3.5-flash, gemini-2.5-flash-lite
	\|-		\|-
	\| '''Groq (OpenAI)''' \|\| <code>https://api.groq.com/openai/v1/chat/completions</code> \|\| llama-3.3-70b-versatile, gpt-oss-120b		\| '''Groq (OpenAI)''' \|\| <code>https://api.groq.com/openai/v1/chat/completions</code> \|\| llama-3.3-70b-versatile, gpt-oss-120b
Line 44:		Line 44:
	Below is a view of the Create page.		Below is a view of the Create page.

	Pick '''OpenAI''' for all LLM whose API is compatible, that's all the LLM but Claude and Gemini. In the example below, the ~~connection type~~ OpenAI ~~is used for Mistral.~~ Please note the Mistral URL.		Pick '''OpenAI''' for all LLM whose API is compatible, that's all the LLM but Claude and Gemini. In the example below, Mistral uses the OpenAI protocol; Please note the Mistral URL.

	[[File:Create Mitral Connection.png\|700px\|center]]		[[File:Create Mitral Connection.png\|700px\|center]]

Command Center Release Notes

Olibouban — Wed, 10 Jun 2026 14:55:06 GMT

LLM Updates

← Older revision		Revision as of 14:55, 10 June 2026
(One intermediate revision by the same user not shown)
Line 8:		Line 8:

	=== LLM Updates ===		=== LLM Updates ===
	The updates to the LLM for Localyzer allow an integration with a broader set of LLMs.		The updates to the LLM for Localyzer allow an integration with a [[LLM \| broader set of LLMs ]]
	* 9313 - UI ChatGPT with URL for private LLM		* 9313 - UI ChatGPT with URL for private LLM
	* 9319 - UI Open up to OpenAI API LLM (Mistral, Grok, etc.)		* 9319 - UI Open up to OpenAI API LLM (Mistral, Grok, etc.)

LLM

Olibouban — Wed, 10 Jun 2026 14:49:51 GMT

Example of LLM Types and Models

← Older revision		Revision as of 14:49, 10 June 2026
(6 intermediate revisions by the same user not shown)
Line 1:		Line 1:
			== Introduction ==
	The connection to an LLM is based on an		The connection to an LLM is based on
			* An API protocol (OpenAI or specific)
	* A URL endpoint, as shown below		* A URL endpoint, as shown below
	* An API token the customer must enter when creating the configuration.		* An API token the customer must enter when creating the configuration.
Line 7:		Line 8:
	* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key		* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key

			== Example of LLM Types and Models ==

	{\| class="wikitable sortable"		{\| class="wikitable sortable"
	\|+ LLM API Providers		\|+ Example LLM API Providers
	! LLM !! API Endpoint URL !! Model Examples		! LLM !! API Endpoint URL !! Model Examples
	\|-		\|-
	\| '''ChatGPT (OpenAI)''' \|\| <code>https://api.openai.com/v1/chat/completions</code> \|\| gpt-5.5, gpt-5.4-mini, o3		\| '''ChatGPT (OpenAI)''' \|\| <code>https://api.openai.com/v1/chat/completions</code> \|\| gpt-5.5, gpt-5.4-mini, o3
	\|-		\|-
	\| '''Claude (~~Anthropic~~)''' \|\| <code>https://api.anthropic.com/v1/messages</code> \|\| claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5		\| '''Claude (Claude)''' \|\| <code>https://api.anthropic.com/v1/messages</code> \|\| claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5
	\|-		\|-
	\| '''DeepSeek''' \|\| <code>https://api.deepseek.com/v1/chat/completions</code> \|\| deepseek-v4-pro, deepseek-v4-flash, deepseek-r1		\| '''DeepSeek (OpenAI)''' \|\| <code>https://api.deepseek.com/v1/chat/completions</code> \|\| deepseek-v4-pro, deepseek-v4-flash, deepseek-r1
	\|-		\|-
	\| '''Fireworks''' \|\| <code>https://api.fireworks.ai/inference/v1/chat/completions</code> \|\| accounts/fireworks/models/llama-v3p3-70b-instruct, accounts/fireworks/models/deepseek-v3		\| '''Fireworks (OpenAI)''' \|\| <code>https://api.fireworks.ai/inference/v1/chat/completions</code> \|\| accounts/fireworks/models/llama-v3p3-70b-instruct, accounts/fireworks/models/deepseek-v3
	\|-		\|-
	\| '''Gemini (~~Google~~)''' \|\| <code>https://generativelanguage.googleapis.com/v1beta/models/</code> \|\| gemini-3.1-pro, gemini-3.5-flash, gemini-2.5-flash-lite		\| '''Gemini (Gemini)''' \|\| <code>https://generativelanguage.googleapis.com/v1beta/models/</code> \|\| gemini-3.1-pro, gemini-3.5-flash, gemini-2.5-flash-lite
	\|-		\|-
	\| '''Groq''' \|\| <code>https://api.groq.com/openai/v1/chat/completions</code> \|\| llama-3.3-70b-versatile, gpt-oss-120b		\| '''Groq (OpenAI)''' \|\| <code>https://api.groq.com/openai/v1/chat/completions</code> \|\| llama-3.3-70b-versatile, gpt-oss-120b
	\|-		\|-
	\| '''Mistral''' \|\| <code>https://api.mistral.ai/v1/chat/completions</code> \|\| mistral-large-3, mistral-small-4, codestral		\| '''Mistral (OpenAI)''' \|\| <code>https://api.mistral.ai/v1/chat/completions</code> \|\| mistral-large-3, mistral-small-4, codestral
	\|-		\|-
	\| '''OpenRouter''' \|\| <code>https://openrouter.ai/api/v1/chat/completions</code> \|\| openai/gpt-5.5, anthropic/claude-sonnet-4-6, google/gemini-3.1-pro		\| '''OpenRouter (OpenAI)''' \|\| <code>https://openrouter.ai/api/v1/chat/completions</code> \|\| openai/gpt-5.5, anthropic/claude-sonnet-4-6, google/gemini-3.1-pro
	\|-		\|-
	\| '''Perplexity''' \|\| <code>https://api.perplexity.ai/chat/completions</code> \|\| sonar-pro, sonar		\| '''Perplexity (OpenAI)''' \|\| <code>https://api.perplexity.ai/chat/completions</code> \|\| sonar-pro, sonar
	\|-		\|-
	\| '''Together AI''' \|\| <code>https://api.together.xyz/v1/chat/completions</code> \|\| meta-llama/Llama-3.3-70B-Instruct-Turbo, deepseek-ai/DeepSeek-V4-Pro		\| '''Together AI (OpenAI)''' \|\| <code>https://api.together.xyz/v1/chat/completions</code> \|\| meta-llama/Llama-3.3-70B-Instruct-Turbo, deepseek-ai/DeepSeek-V4-Pro
	\|-		\|-
	\| '''xAI Grok''' \|\| <code>https://api.x.ai/v1/chat/completions</code> \|\| grok-4, grok-4-fast, grok-3-mini		\| '''xAI Grok (OpenAI)''' \|\| <code>https://api.x.ai/v1/chat/completions</code> \|\| grok-4, grok-4-fast, grok-3-mini
	\|}		\|}

Line 39:		Line 41:
	The LLM models change often. The above are examples as of June 2026.		The LLM models change often. The above are examples as of June 2026.

	Below is a view of the ~~Edit~~ page:		== LLM Creation Information ==
			Below is a view of the Create page.

			Pick '''OpenAI''' for all LLM whose API is compatible, that's all the LLM but Claude and Gemini. In the example below, the connection type OpenAI is used for Mistral. Please note the Mistral URL.

	[[File:~~ChatGPT~~ Connection.png\|700px\|center]]		[[File:Create Mitral Connection.png\|700px\|center]]

	= Token Count =		= Token Count =

File:Create Mitral Connection.png

Olibouban — Wed, 10 Jun 2026 14:41:43 GMT

Olibouban uploaded File:Create Mitral Connection.png

New page

LLM

Olibouban — Wed, 10 Jun 2026 14:34:18 GMT

← Older revision		Revision as of 14:34, 10 June 2026
(3 intermediate revisions by the same user not shown)
Line 1:		Line 1:
	~~The connection to an LLM is based on an API token the customer must enter when creating the configuration. For example, to obtain your key from ChatGPT, please refer to the following page:~~

			The connection to an LLM is based on an
			* A URL endpoint, as shown below
			* An API token the customer must enter when creating the configuration.

			For example, to obtain your key from ChatGPT, please refer to the following page:
	* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key		* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key


			{\| class="wikitable sortable"
			\|+ LLM API Providers
			! LLM !! API Endpoint URL !! Model Examples
			\|-
			\| '''ChatGPT (OpenAI)''' \|\| <code>https://api.openai.com/v1/chat/completions</code> \|\| gpt-5.5, gpt-5.4-mini, o3
			\|-
			\| '''Claude (Anthropic)''' \|\| <code>https://api.anthropic.com/v1/messages</code> \|\| claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5
			\|-
			\| '''DeepSeek''' \|\| <code>https://api.deepseek.com/v1/chat/completions</code> \|\| deepseek-v4-pro, deepseek-v4-flash, deepseek-r1
			\|-
			\| '''Fireworks''' \|\| <code>https://api.fireworks.ai/inference/v1/chat/completions</code> \|\| accounts/fireworks/models/llama-v3p3-70b-instruct, accounts/fireworks/models/deepseek-v3
			\|-
			\| '''Gemini (Google)''' \|\| <code>https://generativelanguage.googleapis.com/v1beta/models/</code> \|\| gemini-3.1-pro, gemini-3.5-flash, gemini-2.5-flash-lite
			\|-
			\| '''Groq''' \|\| <code>https://api.groq.com/openai/v1/chat/completions</code> \|\| llama-3.3-70b-versatile, gpt-oss-120b
			\|-
			\| '''Mistral''' \|\| <code>https://api.mistral.ai/v1/chat/completions</code> \|\| mistral-large-3, mistral-small-4, codestral
			\|-
			\| '''OpenRouter''' \|\| <code>https://openrouter.ai/api/v1/chat/completions</code> \|\| openai/gpt-5.5, anthropic/claude-sonnet-4-6, google/gemini-3.1-pro
			\|-
			\| '''Perplexity''' \|\| <code>https://api.perplexity.ai/chat/completions</code> \|\| sonar-pro, sonar
			\|-
			\| '''Together AI''' \|\| <code>https://api.together.xyz/v1/chat/completions</code> \|\| meta-llama/Llama-3.3-70B-Instruct-Turbo, deepseek-ai/DeepSeek-V4-Pro
			\|-
			\| '''xAI Grok''' \|\| <code>https://api.x.ai/v1/chat/completions</code> \|\| grok-4, grok-4-fast, grok-3-mini
			\|}

			'''Note''': European customers may lean towards Mistral.

			The LLM models change often. The above are examples as of June 2026.

	Below is a view of the Edit page:		Below is a view of the Edit page:

Machine Translation and Translation Management System

Olibouban — Wed, 10 Jun 2026 14:29:02 GMT

Large Language Models (LLM)

← Older revision		Revision as of 14:29, 10 June 2026
(3 intermediate revisions by the same user not shown)
Line 34:		Line 34:

	To create an LLM connection, please see: [[ LLM \| Create LLM Connection ]]		To create an LLM connection, please see: [[ LLM \| Create LLM Connection ]]

	~~LLM using OpenAI: Localyzer uses the OpenAI API to connect to many LLMs, such as, but not limited, to:~~
	*ChatGPT
	*Mistral (Note: might be best suited for European based companies)
	*Grok
	*etc.

	~~The following require a different connection method than the OpenAI API:~~
	* Claude
	* Gemini

	=== Machine Translation (MT) ===		=== Machine Translation (MT) ===

Command Center Release Notes

Olibouban — Tue, 09 Jun 2026 20:02:31 GMT

TSS (Custom Connection)

@@ Line 1: / Line 1: @@
 = Supported Version =
 == Version 4.2.33 (May 2026) ==
@@ Line 253: / Line 279: @@
 ** CVE-2022-45688⁠
 == Command Center 2.2.28 Release Notes (October 2024) ==

Command Center API Reference

Rwilliams — Mon, 08 Jun 2026 20:29:35 GMT

Duplicate Command Center Project

← Older revision		Revision as of 20:29, 8 June 2026
Line 355:		Line 355:
	The <code>createFromTemplateProject</code> command duplicates an existing project with the same configuration as the source project, on a different repository or branch of a repository. The API user will also be set on that target project as it is part of the source project.		The <code>createFromTemplateProject</code> command duplicates an existing project with the same configuration as the source project, on a different repository or branch of a repository. The API user will also be set on that target project as it is part of the source project.

	curl "COMMAND_CENTER_URLapi/createFromTemplateProject" -d '{"username":"API_USER","token":"API_TOKEN","'''source'''": {"group_name": "source_group","project_name": "source_project","module_name": "source_module"},"'''target'''": {"group_name":"target_group","project_name": "target_project","module_name": "target_module"}, "'''~~URL~~'''": "<Repo HTTP URL>", "'''branch'''": "branch"}' --header "Content-Type: application/json"		curl "COMMAND_CENTER_URLapi/createFromTemplateProject" -d '{"username":"API_USER","token":"API_TOKEN","'''source'''": {"group_name": "source_group","project_name": "source_project","module_name": "source_module"},"'''target'''": {"group_name":"target_group","project_name": "target_project","module_name": "target_module"}, "'''url'''": "<Repo HTTP URL>", "'''branch'''": "branch"}' --header "Content-Type: application/json"


Line 361:		Line 361:
	For a target repository name https://github.com/acme/myproject, branch 'translation', with a template called '''acme template dev''' in Command Center using https://github.com, the following call would be make:		For a target repository name https://github.com/acme/myproject, branch 'translation', with a template called '''acme template dev''' in Command Center using https://github.com, the following call would be make:

	curl "http://lingoport.acme.com/command-center/api/createFromTemplateProject" -d '{"username":"APIuser","token":"CTMNzj**********CP","source": {"group_name": "acme","project_name": "template","module_name": "dev"},"target": {"group_name":"acme","project_name": "myproject","module_name": "translation"}, "~~URL~~": "https://github/acme/myproject", "branch": "translation"}' --header "Content-Type: application/json"		curl "http://lingoport.acme.com/command-center/api/createFromTemplateProject" -d '{"username":"APIuser","token":"CTMNzj**********CP","source": {"group_name": "acme","project_name": "template","module_name": "dev"},"target": {"group_name":"acme","project_name": "myproject","module_name": "translation"}, "url": "https://github/acme/myproject", "branch": "translation"}' --header "Content-Type: application/json"

	or		or
Line 381:		Line 381:
	"module_name": "translation"		"module_name": "translation"
	},		},
	"~~URL~~": "https://github/acme/myproject",		"url": "https://github/acme/myproject",
	"branch": "translation"		"branch": "translation"
	}		}

Command Center Release Notes

Olibouban — Fri, 05 Jun 2026 20:13:47 GMT

LRM Import Checks

Olibouban — Mon, 01 Jun 2026 19:29:14 GMT

TRAN_PARAM_MISMATCH LRM Translation Parameter Mismatch Check

← Older revision		Revision as of 19:29, 1 June 2026
Line 51:		Line 51:
	**Issue with single ticks surrounding a parameter with curly brackets.		**Issue with single ticks surrounding a parameter with curly brackets.
	***''''{0}'''' - if there are single ticks surrounding the curly brackets then this means that the curly brackets do '''not''' represent a parameter. The single tick is used as a special character indicating that the curly bracket is a displayable character. So, if the base resource file has '''{0}''' and the imported file has ''"{0}"'' then a parameter mismatch will occur because '''{0}''' is '''not''' a parameter while ''"{0}"'' is a parameter. Parameter mismatch will also occur if the opposite occurs (base resource file has ''"{0}"'' and the imported file has '''{0}''')		***''''{0}'''' - if there are single ticks surrounding the curly brackets then this means that the curly brackets do '''not''' represent a parameter. The single tick is used as a special character indicating that the curly bracket is a displayable character. So, if the base resource file has '''{0}''' and the imported file has ''"{0}"'' then a parameter mismatch will occur because '''{0}''' is '''not''' a parameter while ''"{0}"'' is a parameter. Parameter mismatch will also occur if the opposite occurs (base resource file has ''"{0}"'' and the imported file has '''{0}''')
			*** See: https://unicode-org.github.io/icu/userguide/format_parse/messages/#quotingescaping
	**Number of parameters must match. For example, if the base resource file has 2 {0} parameters then the file that is to be imported must have 2 {0} parameters.		**Number of parameters must match. For example, if the base resource file has 2 {0} parameters then the file that is to be imported must have 2 {0} parameters.

Command Center User's Guide

Olibouban — Thu, 28 May 2026 19:46:38 GMT

Translation Management System & Machine Translator Connections

← Older revision		Revision as of 19:46, 28 May 2026
(2 intermediate revisions by the same user not shown)
Line 66:		Line 66:
	*[[Data_Source_Credentials#Search_and_Sort_Data_Source_Credentials \|Search and Sort Data Source Credentials]]		*[[Data_Source_Credentials#Search_and_Sort_Data_Source_Credentials \|Search and Sort Data Source Credentials]]

	== [[Machine_Translation_and_Translation_Management_System \| Translation Management System & Machine Translator Connections]]==		== [[Machine_Translation_and_Translation_Management_System \| Translation Management System & Machine Translator Connections]] ==

	*[[Machine_Translation_and_Translation_Management_System#~~View_MT_Connections~~ \| ~~View MT~~ Connections]]		*[[Machine_Translation_and_Translation_Management_System#Large_Language_Models_%28LLM%29 \| LLM Connections]]
	*[[Machine_Translation_and_Translation_Management_System#~~Create_and_Configure_MT_Connections~~ \| ~~Create and Configure~~ MT Connections]]		*[[Machine_Translation_and_Translation_Management_System#Machine_Translation_(MT)\| MT Connections]]
	*[[Machine_Translation_and_Translation_Management_System#~~View TMS Connections \| View~~ TMS ~~Connection]]~~		*[[Machine_Translation_and_Translation_Management_System#Translation_Management_Systems_(TMS) \| TMS Connections]]
	*[[Machine_Translation_and_Translation_Management_System#Create and Configure TMS Connections \| ~~Create and Configure~~ TMS Connections]]
	*[[Machine_Translation_and_Translation_Management_System#Search_and_Sort_Connections \| Search and Sort Connections]]		*[[Machine_Translation_and_Translation_Management_System#Search_and_Sort_Connections \| Search and Sort Connections]]

Machine Translation and Translation Management System

Olibouban — Thu, 28 May 2026 19:38:19 GMT

Large Language Models (LLM)

← Older revision		Revision as of 19:38, 28 May 2026
(5 intermediate revisions by the same user not shown)
Line 24:		Line 24:
	LLMs are the up and coming translation systems. When connecting to an LLM, pick the model that fits your needs. LLMs may be public or private, that is the data sent to the LLM may be used outside the company or be kept solely within the company.		LLMs are the up and coming translation systems. When connecting to an LLM, pick the model that fits your needs. LLMs may be public or private, that is the data sent to the LLM may be used outside the company or be kept solely within the company.

	Each LLM type supports multiple models. For instance, Mistral is an LLM that supports over 20 models at the time of this writing, such as <code>mistral-medium-3.5</code> or <code>mistral-nemo-12B</code>, each with its own specialized intent. Each LLM provider updates their model often.

	Some LLM models support passing image as context, some don't. If your projects are configured with Localyzer InContext, make sure the LLM model will make use of it. For example, Claude model <code>claude-haiku-4-5</code> does not seem to pay much attention to an InContext image passed for translation, while Claude model <code>claude-sonnet-4.6</code> does.		Each LLM type supports '''multiple models'''. For instance, Mistral is an LLM that supports over 20 models at the time of this writing, such as <code>mistral-medium-3.5</code> or <code>mistral-nemo-12B</code>, each with its own specialized intent. Each LLM provider updates their model often.


			Some LLM models support passing '''image as context''', some don't. If your projects are configured with Localyzer InContext, make sure the LLM model will make use of it. For example, Claude model <code>claude-haiku-4-5</code> does not seem to pay much attention to an InContext image passed for translation, while Claude model <code>claude-sonnet-4.6</code> does.

	Some are better suited for translation than others.		Some are better suited for translation than others.


	*[[Create ~~OpenAI Supported~~ Connection ~~\| OpenAI~~]]: Localyzer uses the OpenAI API to connect to many LLMs, such as, but not limited, to:		To create an LLM connection, please see: [[ LLM \| Create LLM Connection ]]
	** [[Create ChatGPT Connection \| ChatGPT]]
	** Mistral		LLM using OpenAI: Localyzer uses the OpenAI API to connect to many LLMs, such as, but not limited, to:
	** Grok		*ChatGPT
	** etc.		*Mistral (Note: might be best suited for European based companies)
			*Grok
			*etc.

	*~~[[Create~~ Claude ~~Connection \| Claude]]~~		The following require a different connection method than the OpenAI API:
	*~~[[Create Gemini Connection \|~~ Gemini]]		* Claude
			* Gemini

	=== Machine Translation (MT) ===		=== Machine Translation (MT) ===

LLM

Olibouban — Thu, 28 May 2026 19:29:28 GMT

← Older revision		Revision as of 19:29, 28 May 2026
Line 1:		Line 1:
	The connection to ~~ChatGPT~~ is based on a API token the customer must enter when creating the configuration. To obtain your key from ChatGPT, please refer to the following page:		The connection to an LLM is based on an API token the customer must enter when creating the configuration. For example, to obtain your key from ChatGPT, please refer to the following page:

	* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key		* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key
Line 8:		Line 8:

	= Token Count =		= Token Count =
	When viewing the ~~ChatGPT~~ connection, the number of tokens used up to that point will be displayed.		When viewing the LLM connection, the number of tokens used up to that point will be displayed.

	[[File:ChatGPTtokenCount.png\|center\|600px]]		[[File:ChatGPTtokenCount.png\|center\|600px]]

	When ~~ChatGPT~~ is used for translation, the number of tokens will be shown in the log file for that translation. The total tokens used for the project will be tracked on the Localyzer page.		When an LLM is used for translation, the number of tokens will be shown in the log file for that translation. The total tokens used for the project will be tracked on the Localyzer page.

	[[File:ProjectTokenCount.png\|center\|177px]]		[[File:ProjectTokenCount.png\|center\|177px]]
Line 24:		Line 24:
	== Context Prompting ==		== Context Prompting ==

	If the ~~ChatGPT~~ connection is configured with an InContext server, then when a context has been associated with a string (See [[Individual_Project_Tasks#Context_Capture \| String Manager / Context]]), the context will be passed to ChatGPT to provide the necessary information to better translate that string.		If the LLM connection is configured with an InContext server, then when a context has been associated with a string (See [[Individual_Project_Tasks#Context_Capture \| String Manager / Context]]), the context will be passed to ChatGPT to provide the necessary information to better translate that string.

			Make sure the LLM model takes advantage of the InContext image. Not all models do.

Create ChatGPT Connection

Olibouban — Thu, 28 May 2026 19:27:56 GMT

Olibouban moved page Create ChatGPT Connection to LLM

New page

The connection to ChatGPT is based on a API token the customer must enter when creating the configuration. To obtain your key from ChatGPT, please refer to the following page:

* https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key

Below is a view of the Edit page:

[[File:ChatGPT Connection.png|700px|center]]

= Token Count =
When viewing the ChatGPT connection, the number of tokens used up to that point will be displayed.

[[File:ChatGPTtokenCount.png|center|600px]]

When ChatGPT is used for translation, the number of tokens will be shown in the log file for that translation. The total tokens used for the project will be tracked on the Localyzer page.

[[File:ProjectTokenCount.png|center|177px]]

= Prompting =

For best results with an LLM, prompting is recommended. Localyzer allows for three levels of prompting:

See: [[Prompting]]

== Context Prompting ==

If the ChatGPT connection is configured with an InContext server, then when a context has been associated with a string (See [[Individual_Project_Tasks#Context_Capture | String Manager / Context]]), the context will be passed to ChatGPT to provide the necessary information to better translate that string.

Machine Translation and Translation Management System

Olibouban — Thu, 28 May 2026 19:25:46 GMT

Large Language Models (LLM)

← Older revision		Revision as of 19:25, 28 May 2026
(2 intermediate revisions by the same user not shown)
Line 21:		Line 21:
	The administrator user can select the [[File:CreateIcon.jpg\|20px]] (Create new MT connection) button on the Manage MT Connections page to add new connections. To create a machine translator, the first step is to determine which translator will be connected to. Then provide the system with the appropriate information for that translator.		The administrator user can select the [[File:CreateIcon.jpg\|20px]] (Create new MT connection) button on the Manage MT Connections page to add new connections. To create a machine translator, the first step is to determine which translator will be connected to. Then provide the system with the appropriate information for that translator.

	*[[Create ChatGPT Connection \| ChatGPT]]		=== Large Language Models (LLM) ===
			LLMs are the up and coming translation systems. When connecting to an LLM, pick the model that fits your needs. LLMs may be public or private, that is the data sent to the LLM may be used outside the company or be kept solely within the company.

			Each LLM type supports multiple models. For instance, Mistral is an LLM that supports over 20 models at the time of this writing, such as <code>mistral-medium-3.5</code> or <code>mistral-nemo-12B</code>, each with its own specialized intent. Each LLM provider updates their model often.

			Some LLM models support passing image as context, some don't. If your projects are configured with Localyzer InContext, make sure the LLM model will make use of it. For example, Claude model <code>claude-haiku-4-5</code> does not seem to pay much attention to an InContext image passed for translation, while Claude model <code>claude-sonnet-4.6</code> does.

			Some are better suited for translation than others.


			*[[Create OpenAI Supported Connection \| OpenAI]]: Localyzer uses the OpenAI API to connect to many LLMs, such as, but not limited, to:
			** [[Create ChatGPT Connection \| ChatGPT]]
			** Mistral
			** Grok
			** etc.

			*[[Create Claude Connection \| Claude]]
			*[[Create Gemini Connection \| Gemini]]

			=== Machine Translation (MT) ===
	*[[Create AWS MT Connection\|AWS Translate]]		*[[Create AWS MT Connection\|AWS Translate]]
	*[[Create Google Translate MT Connection\|Google Translate]]		*[[Create Google Translate MT Connection\|Google Translate]]
	*[[Create Microsoft Translator MT Connection\|Microsoft Translator]]		*[[Create Microsoft Translator MT Connection\|Microsoft Translator]]

			=== Translation Management Systems (TMS) ===
	*[[Custom FTP]]		*[[Custom FTP]]
	*[[Smartling]]		*[[Smartling]]

Lingoport Wiki:Zip Files For Prep and Import

Rwilliams — Tue, 26 May 2026 15:46:49 GMT

One Zip File for all Locales, per Prep Kit Number

← Older revision		Revision as of 15:46, 26 May 2026
Line 26:		Line 26:
	* Each file to be translated has a comment at the top of the file which needs to be kept when returning the file from translation vendor.		* Each file to be translated has a comment at the top of the file which needs to be kept when returning the file from translation vendor.
	* The '''translated files''' will be named the same as the original files (so they could be _en.properties even if the content is for French)		* The '''translated files''' will be named the same as the original files (so they could be _en.properties even if the content is for French)
	* The '''translated files''' will be returned in one zip file per locale, in the form: '''<code><group-name>.<project-name>.<kit-version><locale>.zip</code>'''. For example, a translation for French may be named: '''<code>Queens.Champions.1.fr.zip</code>'''.		* The '''translated files''' will be returned in one zip file per locale, in the form: '''<code><group-name>.<project-name>.<kit-version>.<locale>.zip</code>'''. For example, a translation for French may be named: '''<code>Queens.Champions.1.fr.zip</code>'''.

Zip Files For Prep and Import

Olibouban — Thu, 21 May 2026 16:49:20 GMT

Checking the zip file

@@ Line 85: / Line 85: @@
 = Checking the zip file =
-Before pushing the ZIP file, run the zip checker to verify it conforms to the structure shown above.
+Before pushing the ZIP file to the FTP endpoint, run the zip checker to verify it conforms to the structure shown above.
 The bash script is located in this public repository:
 * https://github.com/lingoport-public/Utilities/blob/main/LocalyerZipChecker/check_translation_zip.sh
-Download the file and run it. Here is an example of a good run:
+The Powershell script is located here:
 A bash script that verifies a Lingoport return-translation zip file conforms to the [[Zip_Files_For_Prep_and_Import|One Zip per Locale]] specification before it is imported into Localyzer.

← Older revision		Revision as of 19:46, 28 May 2026
(2 intermediate revisions by the same user not shown)
Line 66:		Line 66:
	*[[Data_Source_Credentials#Search_and_Sort_Data_Source_Credentials \|Search and Sort Data Source Credentials]]		*[[Data_Source_Credentials#Search_and_Sort_Data_Source_Credentials \|Search and Sort Data Source Credentials]]

	== [[Machine_Translation_and_Translation_Management_System \| Translation Management System & Machine Translator Connections]]==		== [[Machine_Translation_and_Translation_Management_System \| Translation Management System & Machine Translator Connections]] ==

	*[[Machine_Translation_and_Translation_Management_System#~~View_MT_Connections~~ \| ~~View MT~~ Connections]]		*[[Machine_Translation_and_Translation_Management_System#Large_Language_Models_%28LLM%29 \| LLM Connections]]
	*[[Machine_Translation_and_Translation_Management_System#~~Create_and_Configure_MT_Connections~~ \| ~~Create and Configure~~ MT Connections]]		*[[Machine_Translation_and_Translation_Management_System#Machine_Translation_(MT)\| MT Connections]]
	*[[Machine_Translation_and_Translation_Management_System#~~View TMS Connections \| View~~ TMS ~~Connection]]~~		*[[Machine_Translation_and_Translation_Management_System#Translation_Management_Systems_(TMS) \| TMS Connections]]
	*[[Machine_Translation_and_Translation_Management_System#Create and Configure TMS Connections \| ~~Create and Configure~~ TMS Connections]]
	*[[Machine_Translation_and_Translation_Management_System#Search_and_Sort_Connections \| Search and Sort Connections]]		*[[Machine_Translation_and_Translation_Management_System#Search_and_Sort_Connections \| Search and Sort Connections]]

← Older revision		Revision as of 20:13, 5 June 2026
Line 13:		Line 13:
	==== String Prompting ====		==== String Prompting ====
	In 4.1, [[Prompting]] was done at the Translation Connection and the Project level. In this release, prompting is also available at the [[Prompting#String_Level_Prompting\|string level]] from [[Individual_Project_Tasks#Expanded_view\| String Manager]].		In 4.1, [[Prompting]] was done at the Translation Connection and the Project level. In this release, prompting is also available at the [[Prompting#String_Level_Prompting\|string level]] from [[Individual_Project_Tasks#Expanded_view\| String Manager]].
	* 9059 - Enhancement: Prompting - String Manager key including new ~~Portal~~ Task		* 9059 - Enhancement: Prompting - String Manager key including new Command Center Task
	* 9061 - Enhancement: Prompting - ChatGpt		* 9061 - Enhancement: Prompting - ChatGpt
	* 9258 - Enhancement: Prompting - String Manager key		* 9258 - Enhancement: Prompting - String Manager key
Line 28:		Line 28:
	* 9048 - Enhancement: Store Min/Max per key-import fails if string length is outside boundary		* 9048 - Enhancement: Store Min/Max per key-import fails if string length is outside boundary
	* 9091 - Enhancement: Resource Issues - include violation of min/max on target files		* 9091 - Enhancement: Resource Issues - include violation of min/max on target files
	* 9271 - Enhancement - ~~Portal~~ task for replacing min/max boundaries for a list of instrument keys		* 9271 - Enhancement - Command Center task for replacing min/max boundaries for a list of instrument keys

	==== Lock Segment ====		==== Lock Segment ====
Line 36:		Line 36:

	* 8349 - Enhancement: CC String Manager - add Lock comment		* 8349 - Enhancement: CC String Manager - add Lock comment
	* 9260 - Call to ~~PortalTask~~.getReplaceDoNotTranslateTask() for setting/unsetting Lock flag		* 9260 - Call to .getReplaceDoNotTranslateTask() for setting/unsetting Lock flag
	* 9261 - 2 new issues associated with 'DoNotTranslate' check.		* 9261 - 2 new issues associated with 'DoNotTranslate' check.
	* 9262 - Key has 'translate="1"' instead of "0" in PXML prep kit file if vendor has InContext set up		* 9262 - Key has 'translate="1"' instead of "0" in PXML prep kit file if vendor has InContext set up