Skip to main content

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

Changelog ↓

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.

InputNotesExample
API Key

Your Google AI Studio API key. Generate API keys here.

AIza...

Vertex AI API​

In order to Authenticate using Vertex:

  1. 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.
  2. Add the following roles to the Service Account:
    1. Vertex AI User or Vertex AI Administrator
    2. Storage Object Viewer
  3. 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.
  4. The top section of the console will show the current project. Select this to display all projects and *Project IDs**.
  5. Regions will be listed here or by navigating to Vertex AI Dashboard from the console.
  6. Enable the Vertex API by navigating to the Library section of APIs & Services. Search 'Vertex' and select enable for the Vertex AI API.
InputNotesExample
Client Email

The email address of the client you would like to connect to.

Private Key

The private key of the client you would like to connect to.

Project ID

Your Google Cloud project ID.

my-project-123
Region

The region to use for API requests. Get your region here.

us-central1

Data Sources​

Select Model​

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

InputNotesExample
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

InputNotesExample
Connection

Select a Google Gemini connection.

Extra Parameters

Extra parameters to pass to the API.

key1:value1,key2:value2
Chat History

JSON string containing the chat history, you can use this parameter to give the model a context of the conversation.

Max Output Tokens

Maximum number of tokens to generate in the response.

1024
Model Name

The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').

gemini-pro
Prompt

The prompt you want to ask to the model.

Write a short story about a robot learning to paint
Safety Settings

JSON string defining safety settings for content generation.

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

Limits token selection to the K most likely next tokens.

40
Top P

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

InputNotesExample
Connection

Select a Google Gemini connection.

File Name

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

InputNotesExample
Aspect Ratio

Aspect ratio of the generated media.

16:9
Connection

Select a Google Gemini connection.

Extra Parameters

Extra parameters to pass to the API.

key1:value1,key2:value2
Language

Language of the generated content.

en
Model Name

The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').

gemini-pro
Number of Images

Number of images to generate.

1
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

InputNotesExample
Aspect Ratio

Aspect ratio of the generated media.

16:9
Connection

Select a Google Gemini connection.

Duration Seconds

Duration of the clip for video generation in seconds.

10
Extra Parameters

Extra parameters to pass to the API.

key1:value1,key2:value2
FPS

FPS of the generated video.

30
Model Name

The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').

gemini-pro
Number of Videos

Number of videos to generate.

1
Person Generation

Whether allow to generate person videos, and restrict to specific ages.

dont_allow
Prompt

Text prompt that typically describes the video to output.

Write a short story about a robot learning to paint
Resolution

Resolution of the generated video.

1080p

Get File​

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

InputNotesExample
Connection

Select a Google Gemini connection.

File Name

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

InputNotesExample
Connection

Select a Google Gemini connection.

Model Name

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

InputNotesExample
Connection

Select a Google Gemini connection.

Fetch All

If true, fetch all items.

false
Page Size

The number of items to return per page.

10
Page Token

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

InputNotesExample
Connection

Select a Google Gemini connection.

Extra Parameters

Extra parameters to pass to the API.

key1:value1,key2:value2
Fetch All

If true, fetch all items.

false
Filter

The filter to apply to the list.

name:gemini-1.5-pro
Page Size

The number of items to return per page.

10
Page Token

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

InputNotesExample
Connection

Select a Google Gemini connection.

Extra Parameters

Extra parameters to pass to the API.

key1:value1,key2:value2
Max Output Tokens

Maximum number of tokens to generate in the response.

1024
Model Name

The name of the model to get information about (e.g., 'gemini-pro', 'gemini-pro-vision').

gemini-pro
Prompt

The text prompt to generate a response for.

Write a short story about a robot learning to paint
Safety Settings

JSON string defining safety settings for content generation.

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

Limits token selection to the K most likely next tokens.

40
Top P

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

InputNotesExample
Connection

Select a Google Gemini connection.

Display Name

The display name of the file.

test.txt
File

The file to upload.

test.txt
File Name

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"
  }
}

Changelog​

2025-06-04​

Added Vertex AI credential handling for improved authentication reliability.

2025-05-23​

Initial release of the Google Gemini component for text generation and analysis.