Documentation
¶
Overview ¶
Package vertexai exposes Google Gen AI capabilities through Vertex AI's GCP backend and Application Default Credentials.
Chat, transcription, speech, and text embedding share the official Google Gen AI SDK protocol mappers with package google while supplying genai.BackendVertexAI, project, and location. Image generation has its own adapter because the current Vertex contract is GenerateContent with Gemini image models, whereas the public Gemini Developer API now recommends the Interactions API. Treating those two transports as interchangeable would leak backend details and preserve deprecated Imagen behavior.
API keys are not used. Authenticate locally with Application Default Credentials or provide an authenticated HTTP client; production workloads normally use a service account or Workload Identity.
Model availability and regions change independently on Vertex AI. Select an explicit model id and location from the current Vertex model documentation.
Index ¶
Constants ¶
const ( Provider = "VertexAI" RequestExtensionKey = "vertexai/request" ResponseExtensionKey = "vertexai/response" SpeechRequestExtensionKey = "vertexai/speech_request" SpeechResponseExtensionKey = "vertexai/speech_response" TranscriptionRequestExtensionKey = "vertexai/transcription_request" TranscriptionResponseExtensionKey = "vertexai/transcription_response" EmbeddingRequestExtensionKey = "vertexai/embedding_request" EmbeddingResponseExtensionKey = "vertexai/embedding_response" ImageRequestExtensionKey = "vertexai/image_request" ImageResponseExtensionKey = "vertexai/image_response" ModelGemini25FlashImage = "gemini-2.5-flash-image" ModelGemini3ProImage = "gemini-3-pro-image" )
const ( // LocationUSCentral1 is the global default for most generative // models (Gemini, Imagen, embedding). LocationUSCentral1 = "us-central1" // LocationGlobal is the multi-region endpoint — useful for // latency-sensitive workloads that can tolerate Google's // internal routing. LocationGlobal = "global" // LocationEuropeWest4 hosts Gemini and Imagen in the EU. LocationEuropeWest4 = "europe-west4" // LocationAsiaSoutheast1 (Singapore) hosts Gemini in APAC. LocationAsiaSoutheast1 = "asia-southeast1" // LocationAsiaNortheast1 (Tokyo) hosts Gemini in Japan. LocationAsiaNortheast1 = "asia-northeast1" )
Common Vertex AI regions. See https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations for the full list — coverage varies by model.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type AudioTTSModel ¶
type AudioTTSModel protocol.AudioTTSModel
func NewAudioTTSModel ¶
func NewAudioTTSModel(config AudioTTSModelConfig) (*AudioTTSModel, error)
type AudioTTSModelConfig ¶
type AudioTTSModelConfig struct {
Client ClientConfig
DefaultOptions tts.Options
}
func (AudioTTSModelConfig) Validate ¶
func (a AudioTTSModelConfig) Validate() error
type AudioTranscriptionModel ¶
type AudioTranscriptionModel = callModel[transcription.Request, transcription.Response]
func NewAudioTranscriptionModel ¶
func NewAudioTranscriptionModel(config AudioTranscriptionModelConfig) (*AudioTranscriptionModel, error)
type AudioTranscriptionModelConfig ¶
type AudioTranscriptionModelConfig struct {
Client ClientConfig
DefaultOptions transcription.Options
}
func (AudioTranscriptionModelConfig) Validate ¶
func (a AudioTranscriptionModelConfig) Validate() error
type ChatConfig ¶
type ChatConfig struct {
Client ClientConfig
DefaultOptions corechat.Options
}
func (ChatConfig) Validate ¶
func (c ChatConfig) Validate() error
type ClientConfig ¶
ClientConfig identifies the Vertex AI project endpoint shared by every modality. HTTPClient remains caller-owned and is never closed by a model; BaseURL is reserved for compatible gateways and test servers.
func (ClientConfig) Validate ¶
func (c ClientConfig) Validate() error
type EmbeddingModel ¶
func NewEmbeddingModel ¶
func NewEmbeddingModel(config EmbeddingModelConfig) (*EmbeddingModel, error)
type EmbeddingModelConfig ¶
type EmbeddingModelConfig struct {
Client ClientConfig
DefaultOptions embedding.Options
}
func (EmbeddingModelConfig) Validate ¶
func (e EmbeddingModelConfig) Validate() error
type ImageGenerationOptions ¶
type ImageGenerationOptions struct {
InputImages []*media.Media `json:"input_images,omitempty"`
AspectRatio string `json:"aspect_ratio,omitempty"`
ImageSize string `json:"image_size,omitempty"`
PersonGeneration string `json:"person_generation,omitempty"`
ProminentPeople string `json:"prominent_people,omitempty"`
OutputCompressionQuality *int32 `json:"output_compression_quality,omitempty"`
}
ImageGenerationOptions carries Vertex-specific GenerateContent controls and optional source images for editing. Store it under ImageRequestExtensionKey.
type ImageModel ¶
type ImageModel struct {
// contains filtered or unexported fields
}
ImageModel implements Gemini native image generation on Vertex AI through GenerateContent. It intentionally does not expose Imagen's Predict endpoint: Google deprecated the Imagen GA endpoints in favor of Gemini image models.
func NewImageModel ¶
func NewImageModel(config ImageModelConfig) (*ImageModel, error)
type ImageModelConfig ¶
type ImageModelConfig struct {
Client ClientConfig
DefaultOptions image.Options
}
func (ImageModelConfig) Validate ¶
func (i ImageModelConfig) Validate() error
Source Files