Skip to main content
Production use of this feature is only available on specific Maia plans. Contact our Sales team for more information.
The Classify transformation component uses the Google BigQuery AI.CLASSIFY function and a Google Gemini model to assign each row of your input data to one or more categories that you define. The component takes text from a single input column and adds a column to the output that contains the category, or categories, assigned to each row.

​
Use case

This component lets you sort unstructured text into categories in your transformation pipeline. For example, you can use it to:
  • Classify customer reviews or survey comments by sentiment or theme.
  • Route support tickets or emails by topic.
  • Tag articles or descriptions with every topic that applies, using the Multi output mode.
The component calls the model once for each input row, so running it on large tables can incur significant inference costs. Usage is also subject to Google BigQuery’s generative AI quotas. To view these charges, read Track costs.

​
Prerequisites

The Google Cloud service account that calls the Gemini model must have the Agent Platform User role (roles/aiplatform.user). Which service account this is depends on the Agent platform connection property:
  • Agent platform connection left blank: Google BigQuery calls the model as the Google Cloud service account that your Maia environment uses to access Google BigQuery. This is the service account in the cloud provider credentials associated with the environment or, for a Hybrid SaaS environment with no associated credentials, the Maia runner‘s own service account.
  • Agent platform connection set: Google BigQuery calls the model as the service account of the Google BigQuery connection. To create a connection and grant its service account the required role, read Run generative AI queries with a Google BigQuery Connection.

​
Properties

​
string
required
A human-readable name for the component.
​
drop-down
required
Select the Gemini model to use. The following options are currently available:
  • gemini-3.5-flash
  • gemini-3.1-flash-lite
  • [Custom]: Use a Gemini model that isn’t listed here, which you name in Custom model.
Google serves gemini-3.5-flash and gemini-3.1-flash-lite only from multi-regional endpoints. Read the AI.CLASSIFY documentation to learn which endpoint Google BigQuery uses for the location your query runs in.
​
string
required
The name of the Gemini model to use—for example, gemini-3.7-flash. Read the AI.CLASSIFY documentation for the Gemini models that Google BigQuery supports.This property is only available when Model is set to [Custom].
​
drop-down
required
Select the input column that contains the text to classify. Only text (STRING) columns are listed.
​
column editor
required
The categories that the model can assign to each row. For each category, enter:
  • Label: The name of the category. Every category must have a label, and each label must be unique. Labels that differ only in case count as the same label.
  • Description: An optional description that tells the model what the category means. You can describe some categories and leave others without a description.
Enter at least two categories and no more than 100. To handle input that doesn’t closely match any category, consider adding an Other category.Toggle Text mode on at the bottom of the dialog to open a multi-line editor that lets you add items in a single block. For more information, read Text mode.To use grid variables, toggle Use Grid Variable on. For more information, read Grid variables.
​
drop-down
required
  • Single: Assigns each row exactly one category, as a STRING value. This is the default setting.
  • Multi: Assigns each row every category that applies, as an ARRAY<STRING> value. The array is empty when no category applies.
​
string
The Google BigQuery connection to use to call the model, in the format <project_id>.<location>.<connection_id>—for example, myproject.us.myconnection. Leave this blank to call the model as the Google Cloud service account that your environment uses to access Google BigQuery.
​
boolean
required
  • Yes: Outputs both your source input columns and the new category column. This also includes input columns that aren’t selected in Input column. This is the default setting.
  • No: Only outputs the new category column.
​
string
required
The name of the column that holds the category or categories for each row. The default is category.When Include input columns is set to Yes, the name must be different from the names of the input columns, ignoring case.

​
Explanation of output

The output contains the input columns (if Include input columns is set to Yes), followed by the category column, named by Result column name. The category column’s contents depend on Output mode:
  • Single: A STRING value containing the category that best fits the row.
  • Multi: An ARRAY<STRING> value containing every category that applies to the row, or an empty array if no category applies.
A row whose model call fails doesn’t stop the run. Its category is NULL, and the output doesn’t show why the call failed. The run fails only if the model call fails for every row.
In Multi mode, a failed row’s NULL becomes an empty array when sampled or written to a table, so it looks the same as a row that matches no category. Check your output for rows with an empty array before you rely on the results.