Google Gemini

6 minutes to read

The Google Gemini extension is a Caspio extension that sends dynamic prompts to Gemini models and stores the AI-generated responses directly in your Caspio table fields. When a configured trigger event occurs on a table, such as a new record being inserted, the extension builds a prompt from that record’s field values, sends it to a Gemini model, and writes the response back into the target fields you specify. Use it to summarize text, classify records, score leads, or extract details from documents.

Before you begin

Before getting started, make sure you have:

A Caspio account with the Integrations Standard Package

Install the extension

Open the Caspio Marketplace and locate the Google Gemini extension. You can also install it from the Integrations page in your Caspio account.
Install the extension.

Create an Agent

After installing the extension, create an agent to define the table to monitor, the events that trigger processing, the prompt to send, and where to store the response.

On the list of extensions, click Open the Google Gemini extension.
On the Agents page, click Create agent.
In the Details step
- Enter a name for your agent.
- Select a profile for this agent, or create one.
- Click Next.
In the Trigger step,
- Select the data source which will be monitored
- Choose the type of event
  - Insert – Send a prompt when a new record is created.
  - Update – Send a prompt when an existing record is updated.
- Choose the event sources that will trigger the agent.
- Click Next.
In the Outgoing data items step:
1. Enter your prompt. You can insert parameters that the extension should use when processing the prompt.
2. Optional: Select one or more file or attachment fields to be analyzed by AI.
3. In the Evaluation right panel, click Evaluate. Once the evaluation result appears below, verify if it matches your expected outcome for this prompt. If not, revise the prompt and evaluate again until you are satisfied with the result.
4. Click Next.
In the Incoming data items step, select the target fields where you want the AI response to be stored. The fields for mapping are based on the evaluation action from the previous step.
Click Create.

Outgoing Data Items

AI prompt: Create a prompt with table fields for the AI to process. Specify response length, value type, or if extra details should be excluded, and adjust for the destination field type (for example, max 255 characters).
File: Include File or Attachment data type fields in the prompt to be analyzed by AI. The supported formats are:
- PDF: Standard PDF, no password or encryption.
- Plain text: TXT, MD, HTML, CSS, CSV, XML, RTF, source code
- Images: PNG, JPEG, WEBP, HEIC, HEIF
- Audio: WAV, MP3, AIFF, AAC, OGG Vorbis, FLAC
- Video: MP4, MPEG, MOV, AVI, FLV, MPG, WEBM, WMV, 3GPP

In the Outgoing data items step, you can evaluate your AI prompt. The evaluation results offer the fields that can potentially be populated when this Agent is executed. Map the fields returned by the evaluation to your table fields in the next step.

Note: Evaluations use the Credits resource in your Caspio account.

Incoming Data Items

Fields available here depend on whether or not you performed the prompt evaluation in the previous step. The final output received from Google Gemini AI model depends on the data types of the target fields that you selected.

If you performed the AI prompt evaluation, all the fields that were returned in the evaluation are available for mapping. The table fields that can be selected depend on the data types of the fields returned in the evaluation.

If you did not perform the AI prompt evaluation, two fields are available:

Response – stores the result of the AI analysis
Response status – stores the success or failure status

Profile Settings

In the profile configuration for the Google Gemini extension, the following settings are available.

Google Gemini account

Choose the Google Gemini account to be used by this extension:

Built-in connection (no further setup) – the extension uses Caspio’s managed Google Gemini API key for all requests. Credit consumption and billing follow Caspio’s standard Credits system. This option is selected by default for all accounts.
Your own account – this option is available to enterprise customers upon request. It allows you to connect the extension to your own Google Gemini account using your personal API key. Select this option and provide your Google Gemini API key in the new field that appears. When using your own key, Credits usage may differ from Caspio’s standard credit system.

AI model

When creating or editing a profile for the Google Gemini extension, you can select which Gemini model the agent will use. Each model differs in reasoning depth, response quality, and Credits consumption.

Recommended by Caspio – automatically uses the model that we recommend for optimal balance of accuracy, speed, and Credits consumption.
3.5 Flash
3.1 Flash-Lite
3.1 Pro

The Pro model produces higher-quality responses but consumes more Caspio Credits per execution than Flash and Flash-Lite. Select the model that best matches the complexity of your task and your Credit budget.

Thinking effort

The Thinking effort determines how much analytical depth the model applies when producing a response. The higher the thinking effort, the more time AI will take to produce a response. Higher thinking effort may result in increased Credits consumption.

Web search

Enable the Use web search for up-to-date responses option to allow Gemini models to include latest online information in their responses. When enabled, the model can fetch relevant web content before generating an answer, improving accuracy for time-sensitive or frequently changing topics.

Web search enhances prompts that depend on current data, such as news, prices, or live statistics. Responses that use web search may consume more Credits due to the additional processing involved.

Instructions

The Instructions field defines how the AI should interpret prompts and respond across all requests associated with the profile. Instructions are always applied and act as persistent guidance for the model.

Resource Usage

This extension uses two types of resources:

Integrations calls: An agent makes 3 integrations calls per task to send, receive, and log, with an additional call for each optional document of File data type (does not apply to Attachment data type).
Credits: Caspio Credits are used for sending requests and receiving the AI response, as well as for using the prompt evaluation feature. The consumption depends on the prompt complexity, the size and complexity of the attached files, the selected model, reasoning effort settings, the response size, and whether or not web search is enabled.