Google Gemini Component

Google Gemini is an offering of advanced AI models developed by Google's DeepMind. Use the component to generate chats, images, and videos.

Component key: google-gemini

Description

Google Gemini is a family of advanced multimodal AI models developed by Google DeepMind.

Use the component to generate chats, images, and videos.

Connections

Google Gemini API

Navigate to Google AI Studio and generate an API key. Enter the key value into the connection configuration of the integration.

Input	Notes	Example
API Key password / Required apiKey	Your Google AI Studio API key. Generate API keys [here](https://makersuite.google.com/app/apikey).	AIza...

Vertex AI API

In order to Authenticate using Vertex:

A Service Account is needed. One may be created in the Google Cloud Platform GCP Console from the IAM & Admin section.
1. From the Service Account, use the Email value as the Client Email input value in the connection configuration.
Add the following roles to the Service Account:
1. Vertex AI User or Vertex AI Administrator
2. Storage Object Viewer
Once a Service Account is created, you will need to generate a Service Account Key
1. Select the Service Account's options, navigate to the Key tab, and select Add Key to create a new key.
2. After creating the key, you will be able to download a JSON file that contains the key information. This key contains sensible data and should be used with caution.
3. Use the key downloaded in the previous step as the Private Key input value in the connection configuration.
The top section of the console will show the current project. Select this to display all projects and *Project IDs**.
Regions will be listed here or by navigating to Vertex AI Dashboard from the console.
Enable the Vertex API by navigating to the Library section of APIs & Services. Search 'Vertex' and select enable for the Vertex AI API.

Input	Notes	Example
Client Email string / Required clientEmail	The email address of the client you would like to connect to.
Private Key text / Required privateKey	The private key of the client you would like to connect to.
Project ID string / Required projectId	Your Google Cloud project ID.	my-project-123
Region string / Required region	The region to use for API requests. [Get your region here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations).	us-central1

Data Sources

Select Model

Select a model from the list of available models. | key: selectModel | type: picklist

Input	Notes
Connection connection / Required connection	Select a Google Gemini connection.

{
  "result": [
    {
      "label": "models/embedding-gecko-001",
      "key": "models/embedding-gecko-001"
    },
    {
      "label": "models/gemini-pro-vision",
      "key": "models/gemini-pro-vision"
    }
  ]
}

Actions

Conversation

Sends a message to the chat. Optionally, historical messages can be provided to continue the chat. | key: sendMessage

Input	Notes	Example
Connection connection / Required connection	Select a Google Gemini connection.
Extra Parameters string Key Value List extraParameters	Extra parameters to pass to the API.	key1:value1,key2:value2
Chat History code history	JSON string containing the chat history, you can use this parameter to give the model a context of the conversation.
Max Output Tokens string maxOutputTokens	Maximum number of tokens to generate in the response.	1024
Model Name string / Required model	The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').	gemini-pro
Prompt string / Required prompt	The prompt you want to ask to the model.	Write a short story about a robot learning to paint
Safety Settings code safetySettings	JSON string defining safety settings for content generation.
Temperature string temperature	Controls randomness in the output. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) make it more focused and deterministic.	0.7
Top K string topK	Limits token selection to the K most likely next tokens.	40
Top P string topP	Limits token selection to tokens with cumulative probability less than P.	0.95

{
  "data": {
    "candidates": [
      {
        "content": {
          "parts": [
            {
              "text": "Okay, let's break down what 'IA' could mean."
            }
          ],
          "role": "model"
        },
        "finishReason": "STOP",
        "avgLogprobs": -0.28463075392904913
      }
    ],
    "modelVersion": "gemini-2.0-flash",
    "usageMetadata": {
      "promptTokenCount": 8,
      "candidatesTokenCount": 1285,
      "totalTokenCount": 1293,
      "promptTokensDetails": [
        {
          "modality": "TEXT",
          "tokenCount": 8
        }
      ],
      "candidatesTokensDetails": [
        {
          "modality": "TEXT",
          "tokenCount": 1285
        }
      ]
    }
  }
}

Delete File

Deletes a file from the service. | key: deleteFile

Input	Notes	Example
Connection connection / Required connection	Select a Google Gemini connection.
File Name string / Required fileName	The name of the file to delete.	test.txt

{
  "data": "Deleted successfully"
}

Generate Image

Generates an image using the Google Generative AI (Gemini) model. | key: generateImage

Input	Notes	Example
Aspect Ratio string aspectRatio	Aspect ratio of the generated media.	16:9
Connection connection / Required connection	Select a Google Gemini connection.
Extra Parameters string Key Value List extraParameters	Extra parameters to pass to the API.	key1:value1,key2:value2
Language string language	Language of the generated content.	en
Model Name string / Required model	The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').	gemini-pro
Number of Images string numberOfImages	Number of images to generate.	1
Prompt string / Required prompt	Text prompt that typically describes the images to output.	Write a short story about a robot learning to paint

Generate Video

Generates a video using the Google Generative AI (Gemini) model. | key: generateVideo

Input	Notes	Example
Aspect Ratio string aspectRatio	Aspect ratio of the generated media.	16:9
Connection connection / Required connection	Select a Google Gemini connection.
Duration Seconds string durationSeconds	Duration of the clip for video generation in seconds.	10
Extra Parameters string Key Value List extraParameters	Extra parameters to pass to the API.	key1:value1,key2:value2
FPS string fps	FPS of the generated video.	30
Model Name string / Required model	The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').	gemini-pro
Number of Videos string numberOfVideos	Number of videos to generate.	1
Person Generation string personGeneration	Whether allow to generate person videos, and restrict to specific ages.	dont_allow
Prompt string / Required prompt	Text prompt that typically describes the video to output.	Write a short story about a robot learning to paint
Resolution string resolution	Resolution of the generated video.	1080p

Get File

Retrieves the file information from the service. | key: getFile

Input	Notes	Example
Connection connection / Required connection	Select a Google Gemini connection.
File Name string / Required fileName	The name of the file to get.	test.txt

{
  "data": {
    "name": "files/ramp",
    "displayName": "Ramp.png",
    "mimeType": "image/png",
    "sizeBytes": "3343",
    "createTime": "2025-05-21T15:28:28.841883Z",
    "expirationTime": "2025-05-23T15:28:28.807436986Z",
    "updateTime": "2025-05-21T15:28:28.841883Z",
    "sha256Hash": "Y2FiZDdjMDIyYTlmYjNkNDU2OGM3YmYwMmNmY2Q4ODliNDE5YWI2NzBjOTM4NDk5MmNkNzhkM2EzM2ZjNzM2Mw==",
    "uri": "https://generativelanguage.googleapis.com/v1beta/files/ramp",
    "state": "ACTIVE",
    "source": "UPLOADED"
  }
}

Get Model Info

Retrieves detailed information about a specific model from the Google Generative AI API. | key: getModelInfo

Input	Notes	Example
Connection connection / Required connection	Select a Google Gemini connection.
Model Name string / Required modelName	The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').	gemini-pro

{
  "data": {
    "name": "models/gemini-2.0-flash",
    "displayName": "Gemini 2.0 Flash",
    "description": "Gemini 2.0 Flash",
    "version": "2.0",
    "tunedModelInfo": {},
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 8192,
    "supportedActions": [
      "generateContent",
      "countTokens",
      "createCachedContent",
      "batchGenerateContent"
    ]
  }
}

List Files

Lists all current project files from the service. | key: listFiles

Input	Default	Notes	Example
Connection connection / Required connection		Select a Google Gemini connection.
Fetch All boolean fetchAll	false	If true, fetch all items.
Page Size string pageSize		The number of items to return per page.	10
Page Token string pageToken		The page token to return.	10

{
  "data": [
    {
      "name": "files/ramp",
      "displayName": "Ramp.png",
      "mimeType": "image/png",
      "sizeBytes": "3343",
      "createTime": "2025-05-21T15:28:28.841883Z",
      "expirationTime": "2025-05-23T15:28:28.807436986Z",
      "updateTime": "2025-05-21T15:28:28.841883Z",
      "sha256Hash": "Y2FiZDdjMDIyYTlmYjNkNDU2OGM3YmYwMmNmY2Q4ODliNDE5YWI2NzBjOTM4NDk5MmNkNzhkM2EzM2ZjNzM2Mw==",
      "uri": "https://generativelanguage.googleapis.com/v1beta/files/ramp",
      "state": "ACTIVE",
      "source": "UPLOADED"
    },
    {
      "name": "files/test",
      "mimeType": "binary/octet-stream",
      "sizeBytes": "65338",
      "createTime": "2025-05-21T02:09:27.231980Z",
      "expirationTime": "2025-05-23T02:09:27.177531840Z",
      "updateTime": "2025-05-21T02:09:27.231980Z",
      "sha256Hash": "NDMzZjUxYTAxMTNiY2QyYzZjMGE2OGRkYzEwMmJhMzk0MGMxZmI3NGZjY2ExMjQwOWVlNTVjOWZjODY3ODZlYg==",
      "uri": "https://generativelanguage.googleapis.com/v1beta/files/test",
      "state": "ACTIVE",
      "source": "UPLOADED"
    }
  ]
}

List Models

Retrieves a list of available models from the Google Generative AI API. | key: listModels

Input	Default	Notes	Example
Connection connection / Required connection		Select a Google Gemini connection.
Extra Parameters string Key Value List extraParameters		Extra parameters to pass to the API.	key1:value1,key2:value2
Fetch All boolean fetchAll	false	If true, fetch all items.
Filter string filter		The filter to apply to the list.	name:gemini-1.5-pro
Page Size string pageSize		The number of items to return per page.	10
Page Token string pageToken		The page token to return.	10

{
  "data": [
    {
      "name": "models/gemini-2.0-flash",
      "displayName": "Gemini 2.0 Flash",
      "description": "Gemini 2.0 Flash",
      "version": "2.0",
      "tunedModelInfo": {},
      "inputTokenLimit": 1048576,
      "outputTokenLimit": 8192,
      "supportedActions": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
      ]
    }
  ]
}

Send Prompt

Send a prompt to the chat and provides a response. | key: generateText

Input	Notes	Example
Connection connection / Required connection	Select a Google Gemini connection.
Extra Parameters string Key Value List extraParameters	Extra parameters to pass to the API.	key1:value1,key2:value2
Max Output Tokens string maxOutputTokens	Maximum number of tokens to generate in the response.	1024
Model Name string / Required model	The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').	gemini-pro
Prompt string / Required prompt	The text prompt to generate a response for.	Write a short story about a robot learning to paint
Safety Settings code safetySettings	JSON string defining safety settings for content generation.
Temperature string temperature	Controls randomness in the output. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) make it more focused and deterministic.	0.7
Top K string topK	Limits token selection to the K most likely next tokens.	40
Top P string topP	Limits token selection to tokens with cumulative probability less than P.	0.95

{
  "data": {
    "candidates": [
      {
        "content": {
          "parts": [
            {
              "text": "The lighthouse keeper, Silas, was a man of routine."
            }
          ],
          "role": "model"
        },
        "finishReason": "STOP",
        "avgLogprobs": -0.5446674455915178
      }
    ],
    "modelVersion": "gemini-2.0-flash",
    "usageMetadata": {
      "promptTokenCount": 6,
      "candidatesTokenCount": 525,
      "totalTokenCount": 531,
      "promptTokensDetails": [
        {
          "modality": "TEXT",
          "tokenCount": 6
        }
      ],
      "candidatesTokensDetails": [
        {
          "modality": "TEXT",
          "tokenCount": 525
        }
      ]
    }
  }
}

Upload File

Uploads a file asynchronously to the Gemini API. | key: uploadFile

Input	Notes	Example
Connection connection / Required connection	Select a Google Gemini connection.
Display Name string displayName	The display name of the file.	test.txt
File data / Required file	The file to upload.	test.txt
File Name string / Required fileName	The name of the file to get.	test.txt

{
  "data": {
    "name": "files/ramp",
    "displayName": "Ramp.png",
    "mimeType": "image/png",
    "sizeBytes": "3343",
    "createTime": "2025-05-21T15:28:28.841883Z",
    "expirationTime": "2025-05-23T15:28:28.807436986Z",
    "updateTime": "2025-05-21T15:28:28.841883Z",
    "sha256Hash": "Y2FiZDdjMDIyYTlmYjNkNDU2OGM3YmYwMmNmY2Q4ODliNDE5YWI2NzBjOTM4NDk5MmNkNzhkM2EzM2ZjNzM2Mw==",
    "uri": "https://generativelanguage.googleapis.com/v1beta/files/ramp",
    "state": "ACTIVE",
    "source": "UPLOADED"
  }
}

Google Gemini is an offering of advanced AI models developed by Google's DeepMind. Use the component to generate chats, images, and videos.

Description​

Connections​

Google Gemini API​

Vertex AI API​

Data Sources​

Select Model​

Actions​

Conversation​

Delete File​

Generate Image​

Generate Video​

Get File​

Get Model Info​

List Files​

List Models​

Send Prompt​

Upload File​