Gemini

The Gemini connector enables you to generate content through chat responses using the Gemini model. The Gemini connector currently contains one action: Chat.

Prerequisites

To use the Gemini connector, you first need to connect your Google AI Studio with Automate using the following steps:

1. Log in to your Contentstack account and click the Automate icon from the left navigation panel.
2. Select your project and then the automation.
3. Click Configure Action Step from the left navigation panel and then Action Step to configure third-party services.
4. Within the Choose Connector, click the Gemini connector.
5. Under Choose an Action, select the Chat action.
6. In the Configure Action section, click + Add New Account to add your Google AI Studio account.
7. In the Authorize modal, provide details such as Title, and API Key from the Google AI Studio.

   To generate an API key in Google AI Studio, follow the steps below:

   1. Go to the Google AI Studio.
   2. Click the Get API Key option in the left navigation and then click the Create API Key button.
   3. From the Search Google Cloud projects drop-down, select an existing Google Cloud project.
   4. Once done, click Create API key in existing project button.
8. Click the Authorize button.

This sets up your Google AI Studio account for the Gemini connector.

Set up the Gemini Connector

Perform the following steps to set up the Gemini connector:

1. From the left navigation panel, click Configure Action Step.
2. Then, click Action Step to configure third-party services.
3. Within the Configure Action Step, click the Gemini connector.
4. Under Choose an Action, you will see the Chat action.

Chat

The Chat action returns the chat response(s) from the Gemini model. To use the Chat action, follow the steps below:

1. Under Choose an Action tab, select the Chat action.
2. On the Chat Configure Action page, enter the details given below:
   1. Click + Add New Account button to connect your Gemini account as shown in the Prerequisites step.
   2. Select the Model from the dropdown list to generate content for the chat responses.

      Note: Different models are available to different users, based on the account the user holds such as paid accounts. You must check your account access before selecting the model.

   3. Enter the System Instruction Text to provide specific guidance or directives to the model to help it understand the context and generate an appropriate response based on the provided prompt text.
   4. Select a User Prompt (text or image) to generate response(s).

      Click + Add User Prompt to enter multiple prompts.

      When Text prompt is selected:

      1. From the Select Message Type drop-down, select the Text type.
      2. In the Input Text field, enter the input text to generate a response.

      When Image is selected:

      1. From the Select Message Type drop-down, select the Image type.
      2. In the Image URL field, enter the URL of the image.
      3. Select the MIME Type for the image.
   5. Click the Show Optional Fields toggle button to use these optional fields:
      1. Select the Response Type as either Text, JSON or Structured Output. For the Response Type as JSON or Structured Output, the output is produced in a valid JSON format.

         When selecting Structured Output as the Response Type, you must provide a valid JSON-formatted structured schema to ensure a properly formatted response.

         Note:

         • To use Structured Outputs, all fields or function parameters must be marked as required.
         • A schema can include up to 100 object properties in total, with a maximum of 5 levels of nesting.
         • Structured Output generates only the specified keys and values. To enable this, you must set additionalProperties: false.

         Additional Resource: See the JSON Schema documentation for more details.

      2. Enter the Number of Tokens to generate the content.
      3. Enter a value for the Randomness of Responses of the generated content. 0 being the most precise and 2 being the most random content predictions. This must be within the range of 0 to 2.
      4. Enter the Top-P value to define how the model selects tokens for output. For instance, if tokens A, B, and C have probabilities of 0.3, 0.2, and 0.1; then entering a Top-P value as 0.5, the model chooses either A or B as the next token using temperature and excludes C. This must be within the range of 0 to 1.
      5. Enter the Top-K value to define how the model selects tokens for output. Entering a Top-K value of 1 implies that the next chosen token is the most likely among all tokens in the model's vocabulary. Top-K value of 3 means that the next token is selected from the three most probable tokens using temperature. This must be within the range of 1 to 40.
      6. Enter the Count of Response to fetch the desired number of responses for the user prompt. If you enter 5, then 5 responses will be displayed in the output.
      7. You can mark the Sanitize text checkbox to remove special characters or spaces from the chat response. Enabling this checkbox, eliminates any special characters or spaces in the chat response, resulting in a clean and compatible text.
3. Click Proceed.
4. Check if the details are correct. If yes, then click Test Action.
5. You will get the response(s). Once set, click Save and Exit.

This completes the Gemini connector’s setup.