Google configuration

Package github.com/digitallysavvy/go-ai/pkg/providers/google. Create a provider with google.New(google.Config{...}). When APIKey is empty, the provider reads GOOGLE_GENERATIVE_AI_API_KEY.

The tables on this page are generated from the Go source. For usage, see the Google provider page.

Config

Field	Type	Description
APIKey	string	APIKey is the Google API key
BaseURL	string	BaseURL is the base URL for the Google API (default: https://generativelanguage.googleapis.com)
Headers	map[string]string	Headers are custom HTTP headers to include in requests.
Name	string	Name overrides the provider name returned by Provider.Name(). Defaults to "google.generative-ai".
HTTPClient	*http.Client	HTTPClient overrides the HTTP client used for requests.

Model factories

Method	Returns
LanguageModel(id)	A Gemini language model.
Interactions(id), InteractionsAgent(agent), InteractionsManagedAgent(id)	Language models that use the Interactions API.
EmbeddingModel(id)	An embedding model.
ImageModel(id)	An image generation model.
SpeechModel(id)	A speech synthesis model.
TranscriptionModel(id)	A transcription model.
VideoModel(id)	A video generation model.
RerankingModel(id)	A reranking model.
Files()	The Files API client.

GoogleEmbeddingProviderOptions

Field	Type	Description
Parts	[]EmbeddingPart	Parts provides additional multimodal content parts alongside the text input. Each element corresponds to a single embedding value and is appended to that value's content.parts in the API request.
Content	[][]EmbeddingPart	Content provides TypeScript-compatible per-value multimodal content. Each entry corresponds to the embedding value at the same index. A nil entry is text-only; a non-nil entry must contain at least one part.
OutputDimensionality	*int	OutputDimensionality optionally truncates the embedding vector length.
TaskType	string	TaskType maps to the Google embedding taskType request field.

GoogleSpeechModelOptions

Field	Type	Description
MultiSpeakerVoiceConfig	map[string]interface{}	MultiSpeakerVoiceConfig configures Gemini multi-speaker TTS. When set it takes precedence over the top-level voice.

GoogleVideoModelOptions

Field	Type	Description
PersonGeneration	*string
NegativePrompt	*string
ReferenceImages	[]googleVideoReferenceImageOpt

GoogleInteractionsProviderOptions

Field	Type	Description
PreviousInteractionID	string
Store	*bool
MediaResolution	string
SystemInstruction	string
ResponseModalities	[]string
ServiceTier	string
ThinkingLevel	string
ThinkingSummaries	string
ResponseFormat	[]map[string]interface{}	ResponseFormat holds raw (camelCase) response_format entries from providerOptions.google.responseFormat, e.g. {"type":"video","aspectRatio":"16:9",...}. Converted to snake_case wire entries in buildArgs.
ImageConfig	map[string]interface{}
Agent	string
AgentConfig	map[string]interface{}
Environment	interface{}
PollingTimeoutMs	int
Background	*bool