Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.phidata.com/llms.txt

Use this file to discover all available pages before exploring further.

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

​
Authentication

Authenticate with Gcloud

​
Example

Use Gemini with your Agent: 
from phi.agent import Agent, RunResponse
from phi.model.vertexai import Gemini

agent = Agent(
    model=Gemini(id="gemini-1.5-flash"),
    markdown=True
)

# Get the response in a variable
# run: RunResponse = agent.run("Share a 2 sentence horror story.")
# print(run.content)

# Print the response on the terminal
agent.print_response("Share a 2 sentence horror story.")

​
Params

ParameterTypeDefaultDescription
idstr"claude-3-5-sonnet-20240620"The specific model ID used for generating responses.
namestr"Claude"The name identifier for the agent.
providerstr"Anthropic"The provider of the model.
max_tokensOptional[int]1024The maximum number of tokens to generate in the response.
temperatureOptional[float]-The sampling temperature to use, between 0 and 2. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic.
stop_sequencesOptional[List[str]]-A list of sequences where the API will stop generating further tokens.
top_pOptional[float]-Nucleus sampling parameter. The model considers the results of the tokens with top_p probability mass.
top_kOptional[int]-The number of highest probability vocabulary tokens to keep for top-k-filtering.
request_paramsOptional[Dict[str, Any]]-Additional parameters to include in the request.
api_keyOptional[str]-The API key for authenticating requests to the service.
client_paramsOptional[Dict[str, Any]]-Additional parameters for client configuration.
clientOptional[AnthropicClient]-A pre-configured instance of the Anthropic client.