LLM Translate

Add an LLM Translate node to your Data Flow. This node translates values from an existing column into a new language, and adds those translations to a new column. The translation is generated automatically using the Model's LLM.

Note: It is important to note that any of the Generative Artificial Intelligence (Gen-AI) nodes could potentially create a performance overhead, depending on the size of your model. You should, therefore, consider the inclusion of these nodes carefully, and perhaps configure your Sync Model settings with reference to your requirements. For more information, see Data Flow Ribbon.

Language limitations: Your available languages may be limited to a particular subset in the Admin Console.

Add an LLM Translate node

This task is part of a "data preparation" or "transformation" stage that lets you cleanse and improve your data before you write it to your target database.

Before you begin

You should have a Data Flow that includes at least one datasource and one or more Tables. You are going to translate the content in one of the table's columns, creating a new column to store the translation.

If you do not have permission to add this type of node, you will not see the Gen-AI options in the Data Flow > Elements list.

Procedure

From the Data Flow page in Model Pro:

  1. Click Gen-AI in the left-hand menu and, from the sub-menu, drag-and-drop LLM Translate onto the canvas.
  2. Connect the Table that contains the column you want to translate to the LLM Translate node.

    3. Note: The connection is created by selecting the "end connector" (red arrow) on the Table node and then dragging your cursor to the "start connector" (blue box) on the LLM Translate node.

  3. Select LLM Translate and, from the Properties panel, set:
    • Select Column: Select the name of the Column that you want to create translations for.
    • New Column Name: By default, the name Translation is supplied for the new column. You are advised to supply a more meaningful name for your new column; for example, if you are translating the column "Country Name" into German you might want to call the new column "Country Name DE".
    • From (Optional): Either select the source language from the drop-down list or, if the language is not present in the list, type its name into the field. You should not, typically, need to supply a source language; the AI tool should be able to work out the source language from the values in the source column. This option is typically used where that might not be the case, for example, where you are transforming strings from English US to English UK for geographical localizations.
    • To: Either select the target language (the language you want to translate the column into) from the drop-down list or type its name into the field.
  4. Click Preview (the two buttons are shown with green arrows in the following example) and check that your translated column is created as you expect in the Preview panel.

    5. Notes:

    • If the AI tool is unable to create a translated column, it may either replicate the content of the original column (so you end up with two columns with the same data) or it may leave the column empty.
    • The preview creates a fixed number of rows (50 by default). To increase the number of rows, change the Preview Size option. For more information, see Datasource Preview.

  5. Click Save at any time to save your changes.

You can now continue building your Data Flow as usual. Typically adding a Target to your Data Flow; your Target is the database that you want to use to store your processed data.

What next?

Once you have completed your Data Flow, what you do with your newly translated data depends on your requirements:

  • You can use your newly translated column in place of the column data that you translated for all of your users.
  • You can store both columns and use the modeling translation feature to configure the language data so that users can select from the available languages.

In either case, you need to configure the model to use the correct column data in the Translations Panel.

Example: LLM Translation

Related Tasks

There are a number of mechanisms that allow you to set up translations of different data, using AI or otherwise:

  • To translate content item metadata (including automatic translations using AI), see Translations Panel.
  • To translate the formula name to be used for metadata and queries (not using AI), see Multi-lingual Formulas.
  • To translate the dynamic text in Presentations into the user's application language automatically using AI, see Auto Translate.