Google Gemini (Beta) Prompt activity

Introduction

A Google Gemini (Beta) Prompt activity, using its Google Gemini (Beta) connection, sends a prompt to the specified model in Google Gemini and is intended to be used as a target to consume data in an operation.

Create a Google Gemini (Beta) Prompt activity

An instance of a Google Gemini (Beta) Prompt activity is created from a Google Gemini (Beta) connection using its Prompt activity type.

To create an instance of an activity, drag the activity type to the design canvas or copy the activity type and paste it on the design canvas. For details, see Creating an activity instance in Component reuse.

An existing Google Gemini (Beta) Prompt activity can be edited from these locations:

• The design canvas (see Component actions menu in Design canvas).
• The project pane's Components tab (see Component actions menu in Project pane Components tab).

Configure a Google Gemini (Beta) Prompt activity

Follow these steps to configure a Google Gemini (Beta) Prompt activity:

• Step 1: Enter a name and specify settings
  Provide a name for the activity, select a model, and specify a prompt and optional settings.

• Step 2: Review the data schemas
  Any request or response schemas are displayed.

Step 1: Enter a name and specify settings

In this step, provide a name for the activity, select a model, and specify a prompt and optional settings. Each user interface element of this step is described below.

• Name: Enter a name to identify the activity. The name must be unique for each Google Gemini (Beta) Prompt activity and must not contain forward slashes / or colons :.

• Choose option: Specify the choose option to be used, either List all models or Enter model identifier.

• List all models: Select this option to choose from a list of models retrieved from Google Gemini:

  • Select a model: This section displays models available in the Google Gemini (Beta) endpoint.

    • Selected model: After a model is selected, it is listed here.

    • Search: Enter any column's value into the search box to filter the list of models. The search is not case-sensitive. If models are already displayed within the table, the table results are filtered in real time with each keystroke. To reload models from the endpoint when searching, enter search criteria and then refresh, as described below.

    • Refresh: Click the refresh icon or the word Refresh to reload models from the Google Gemini (Beta) endpoint. This may be useful if models have been added to Google Gemini. This action refreshes all metadata used to build the table of models displayed in the configuration.

    • Selecting a model: Within the table, click anywhere on a row to select a model. Only one model can be selected. The information available for each model is fetched from the Google Gemini (Beta) endpoint:

      • Display Name: The name of the model.

      • ID: The ID of the model.

      • Description: The description of the model.

    Tip

    If the table does not populate with available models, the Google Gemini (Beta) connection may not be successful. Ensure you are connected by reopening the connection and retesting the credentials.

    Alternatively, the model can be specified in the Model identifier field or provided in the request transformation. If a model is specified in multiple places, this order of precedence is followed:

    1. A model provided in the request transformation overrides all fields below.
    2. A model specified in the Model identifier field overrides the remaining field below, even if List all models is selected.
    3. A model selected in the Select a model list has the least precedence.

• Enter model identifier: Select this option to manually enter the name of a model in Google Gemini:

  • Model ID: Enter the model ID.

• Prompt: Enter the text to prompt the model with.

• Optional settings: Click to expand additional optional settings:

  • Randomness and diversity:

    • Temperature: Enter a temperature parameter. This parameter's value can range between 0 and 1, for example: 0.5.
    • Top K: Enter a Top K parameter. This parameter's value must be greater than 0 and is 40 by default.
    • Top P: Enter a Top P parameter. This parameter's value can range between 0 and 1 and is 0.95 by default.

  • Length:

    • Max Output Tokens: Enter a maximum output token parameter. The maximum number of tokens allowed depends on the chosen model.

  • Continue on error: Select to continue the activity execution if an error is encountered for a dataset in a batch request. If any errors are encountered, they are written to the operation log.

• Save & Exit: If enabled, click to save the configuration for this step and close the activity configuration.

• Next: Click to temporarily store the configuration for this step and continue to the next step. The configuration will not be saved until you click the Finished button on the last step.

• Discard Changes: After making changes, click to close the configuration without saving changes made to any step. A message asks you to confirm that you want to discard changes.

Step 2: Review the data schemas

Any request or response schemas are displayed. Each user interface element of this step is described below.

• Data schema: These data schemas are inherited by adjacent transformations and are displayed again during transformation mapping.

  Note

  Data supplied in a transformation takes precedence over the activity configuration.

  The Google Gemini (Beta) connector uses the Gemini API. Refer to the API documentation for additional information.

• Refresh: Click the refresh icon or the word Refresh to regenerate schemas from the Google Gemini (Beta) endpoint. This action also regenerates a schema in other locations throughout the project where the same schema is referenced, such as in an adjacent transformation.

• Back: Click to temporarily store the configuration for this step and return to the previous step.

• Finished: Click to save the configuration for all steps and close the activity configuration.

• Discard Changes: After making changes, click to close the configuration without saving changes made to any step. A message asks you to confirm that you want to discard changes.

Next steps

After configuring a Google Gemini (Beta) Prompt activity, complete the configuration of the operation by adding and configuring other activities, transformations, or scripts as operation steps. You can also configure the operation settings, which include the ability to chain operations together that are in the same or different workflows.

Menu actions for an activity are accessible from the project pane and the design canvas. For details, see Activity actions menu in Connector basics.

Google Gemini (Beta) Prompt activities can be used as a target with these operation patterns:

• Transformation pattern
• Two-transformation pattern (as the first or second target)

To use the activity with scripting functions, write the data to a temporary location and then use that temporary location in the scripting function.

When ready, deploy and run the operation and validate behavior by checking the operation logs.