Gemini

GeminiTools are a set of tools that allow an Agent to interact with Google AI API services for generating images and videos.

Prerequisites

Before using GeminiTools, make sure to have the google-genai library installed and the credentials configured.

Install dependencies:
```
1uv pip install google-genai kern-ai
```

Set your credentials:

For Gemini API:

1export GOOGLE_API_KEY="your-google-genai-api-key"

For Vertex AI:

1export GOOGLE_CLOUD_PROJECT="your-google-cloud-project-id"
2export GOOGLE_CLOUD_LOCATION="your-google-cloud-location"
3export GOOGLE_GENAI_USE_VERTEXAI=true

Initialization

Import GeminiTools and add it to your Agent's tool list.

1from kern.agent import Agent
2from kern.tools.models.gemini import GeminiTools
3
4agent = Agent(
5    tools=[GeminiTools()],
6    )

Usage Examples

GeminiTools can be used for a variety of tasks. Here are some examples:

Image Generation

1from kern.agent import Agent
2from kern.models.openai import OpenAIResponses
3from kern.tools.models.gemini import GeminiTools
4from kern.utils.media import save_base64_data
5
6agent = Agent(
7    model=OpenAIResponses(id="gpt-5.2"),
8    tools=[GeminiTools()],
9    )
10
11response = agent.run("Create an artistic portrait of a cyberpunk samurai in a rainy city")
12if response.images:
13    save_base64_data(response.images[0].content, "tmp/cyberpunk_samurai.png")

Video Generation

Note

Video generation requires Vertex AI.

1from kern.agent import Agent
2from kern.models.openai import OpenAIResponses
3from kern.tools.models.gemini import GeminiTools
4from kern.utils.media import save_base64_data
5
6agent = Agent(
7    model=OpenAIResponses(id="gpt-5.2"),
8    tools=[GeminiTools(vertexai=True)],
9        debug_mode=True,
10)
11
12agent.print_response(
13    "Generate a 5-second video of a kitten playing a piano",
14)
15response = agent.run("Generate a 5-second video of a kitten playing a piano")
16if response.videos:
17    for video in response.videos:
18        save_base64_data(video.content, f"tmp/kitten_piano_{video.id}.mp4")

Toolkit Params

Parameter	Type	Default	Description
`api_key`	`Optional[str]`	`None`	Google API key for authentication. If not provided, uses GOOGLE_API_KEY environment variable.
`vertexai`	`bool`	`False`	Whether to use Vertex AI instead of standard Gemini API. Required for video generation.
`project_id`	`Optional[str]`	`None`	Google Cloud project ID. Required when using Vertex AI.
`location`	`Optional[str]`	`None`	Google Cloud location/region. Required when using Vertex AI.
`image_generation_model`	`str`	`"imagen-3.0-generate-002"`	Model to use for image generation.
`video_generation_model`	`str`	`"veo-2.0-generate-001"`	Model to use for video generation.
`enable_generate_image`	`bool`	`True`	Enable the image generation function.
`enable_generate_video`	`bool`	`True`	Enable the video generation function.
`all`	`bool`	`False`	Enable all available functions. When True, all enable flags are ignored.

Toolkit Functions

Function	Description
`generate_image`	Generate an image based on a text prompt
`generate_video`	Generate a video based on a text prompt