Gemini - VertexAI

VertexAI is Google’s cloud platform for building, training, and deploying machine learning models.

We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

Authentication

Use Gemini with your Agent:

View more examples here.

Parameter	Type	Default	Description
`id`	`str`	`"gemini-2.0-flash-exp"`	The specific model ID used for generating responses.
`name`	`str`	`"Gemini"`	The name identifier for the agent.
`provider`	`str`	`"VertexAI"`	The provider of the model.
`function_declarations`	`Optional[List[FunctionDeclaration]]`	`None`	A list of function declarations that the model can utilize during the response generation process.
`generation_config`	`Optional[Any]`	`None`	Configuration settings for the generation process, such as parameters for controlling output behavior.
`safety_settings`	`Optional[Any]`	`None`	Settings related to safety measures, ensuring the generation of appropriate and safe content.
`generative_model_request_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters for the generative model requests.
`client`	`Optional[GenerativeModel]`	`None`	A pre-configured instance of the Gemini client.

Gemini is a subclass of the Model class and has access to the same params.