class LittleGhost::Providers::VertexAI

Connects a Model to Gemini models hosted by Google Vertex AI.

It sends the same request content as the Gemini adapter to the configured Google Cloud project and location. A trusted credential resolver supplies each access token. Cancellation, deadlines, normalized streaming events, and ProviderError behavior match Providers::Gemini.

Public Class Methods

new (model:, project:, location: "global", access_token: nil, credential_resolver: nil, base_url: nil, **arguments)

Source

# File lib/little_ghost/providers/vertex_ai.rb, line 16
def initialize(model:, project:, location: "global", access_token: nil, credential_resolver: nil,
  base_url: nil, **arguments)
  @project = project.to_s
  @location = location.to_s
  @credential_resolver = credential_resolver || CredentialResolver.new(access_token:)
  raise ConfigurationError, "Vertex AI project is required" if @project.empty?

  base_url ||= "https://#{@location}-aiplatform.googleapis.com/v1/"
  super(api_key: "unused", model:, base_url:, **arguments)
end

Creates a Vertex AI client for a Google Cloud project and location.

Calls superclass method LittleGhost::Providers::Gemini::new