Skip to main content

XTM Cloud 26.2

Connecting XTM Cloud to your OpenAI GPT engine

Important

OpenAI GPT credentials have been moved to Configuration > Settings AI Control Center > LLM configuration tab. For details, see OpenAI GPT LLM configuration.

Procedure. To connect XTM Cloud account to your OpenAI GPT engine:

  1. To connect OpenAI GPT to XTM Cloud, enter your OpenAI GPT credentials in Configuration > Settings AI Control Center > LLM configuration tab. For details, see OpenAI GPT LLM configuration.

  2. To configure the use of OpenAI GPT as an MT engine, follow the steps described below.

  3. Select Configuration > Settings > Translation.

  4. Select the Machine translation tab.

  5. In the MT engines section, select the OpenAI checkbox.

    Result: the OpenAI GPT section is displayed below the General options section.

  6. In the OpenAI GPT section, fill in the relevant fields:

    Table 42. OpenAI GPT – configuration settings

    Setting

    Description

    Mandatory/Optional

    Type

    Valid values

    Default setting

    Use this setting to specify whether this MT engine should automatically be enabled at customer and project level.

    Optional

    Checkbox

    • Cleared (default).

      If you select this setting, Project Managers need to select the relevant checkbox to use this MT engine at customer and project level.

    • Selected.

      If you select this setting, this MT engine is automatically selected at customer and project level. Project Managers need to clear the relevant checkbox to disable this MT engine at customer and project level.

    Send text for matching

    Use this setting to specify the stage at which content is to be sent to the MT engine.

    Mandatory

    Radio buttons

    • In XTM Workbench (default).

      When this setting is selected, the text is only sent to an MT engine when a user enters a segment in XTM Workbench in Edit mode. The translation is provided on a segment-to-segment basis.

    • After analysis (option inactive).

    • After analysis and in XTM Workbench (option inactive).

    Use auto inline tag placement (for the Auto Inline Tags feature)

    The Auto Inline Tags feature uses the XTM NLP framework for the automatic placement of inline tags in the machine translation output.

    Mandatory

    Radio buttons

    • Never (option inactive).

    • Only incorrect inline tags (option inactive).

    • Always (default).

      When this setting is selected, after receiving translation from the MT system, the auto-insert mechanism works for all matches received from the MT engine.

      Note

      We recommend that you use this option because Open AI does NOT support inline tags.


  7. At the bottom of the page, select Save.

Result: OpenAI GPT is displayed in the Configuration > Settings > Translation > Machine Translation section.

Project Managers can enable or disable OpenAI GPT at customer level. They can also select a different connection method and/or connection details for the relevant customer.

At project level, Project Managers can add OpenAI GPT to a new project while creating it, or to an existing one in the Project Editor. Additionally, they can enable or disable it for a particular language pair. Segments processed by OpenAI GPT are counted as MT matches in the project Metrics and Statistics, in the Project Editor. Project Managers can also enable or disable OpenAI GPT for a particular project template(s).

In XTM Workbench, OpenAI GPT MT matches are labeled as OpenAI GPT MT.

Important

If a project is subcontracted, your machine translation (MT) settings are inherited by your subcontractor (LSP) and their Linguists.

Neither LSP Project Managers nor LSP Linguists can change these settings.

In this section: