Documentation
¶
Index ¶
- type GenerateContent
- func New(ctx context.Context, apiKey, modelName string, retryCfg ...retry.Config) (*GenerateContent, error)
- func NewVertexAI(ctx context.Context, project, location, modelName string, ...) (*GenerateContent, error)
- func NewVertexAIWithOptions(ctx context.Context, project, location, modelName string, opts ...Option) (*GenerateContent, error)
- func NewWithOptions(ctx context.Context, apiKey, modelName string, opts ...Option) (*GenerateContent, error)
- type Option
- type ThinkingLevel
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type GenerateContent ¶
type GenerateContent struct {
// contains filtered or unexported fields
}
GenerateContent implements model.LLM using the Gemini GenerateContent API.
func New ¶
func New(ctx context.Context, apiKey, modelName string, retryCfg ...retry.Config) (*GenerateContent, error)
New creates a new GenerateContent instance for the Gemini Developer API. apiKey is required. modelName is the identifier of the Gemini model to use (e.g. "gemini-2.0-flash", "gemini-2.5-pro"). retryCfg is optional; when provided it enables automatic retry with exponential backoff on transient errors (rate limits, 5xx, network issues).
func NewVertexAI ¶
func NewVertexAI(ctx context.Context, project, location, modelName string, retryCfg ...retry.Config) (*GenerateContent, error)
NewVertexAI creates a new GenerateContent instance backed by Google Cloud Vertex AI. project is the GCP project ID, location is the region (e.g. "us-central1"), and modelName is the Gemini model identifier (e.g. "gemini-2.0-flash"). Authentication uses Application Default Credentials (ADC) by default; set up credentials via `gcloud auth application-default login` or a service account key file pointed to by the GOOGLE_APPLICATION_CREDENTIALS environment variable. retryCfg is optional; when provided it enables automatic retry with exponential backoff on transient errors (rate limits, 5xx, network issues).
func NewVertexAIWithOptions ¶ added in v0.0.7
func NewVertexAIWithOptions(ctx context.Context, project, location, modelName string, opts ...Option) (*GenerateContent, error)
NewVertexAIWithOptions creates a new GenerateContent instance backed by Google Cloud Vertex AI with explicit adapter options.
func NewWithOptions ¶ added in v0.0.7
func NewWithOptions(ctx context.Context, apiKey, modelName string, opts ...Option) (*GenerateContent, error)
NewWithOptions creates a new GenerateContent instance for the Gemini Developer API with explicit adapter options.
func (*GenerateContent) GenerateContent ¶
func (g *GenerateContent) GenerateContent(ctx context.Context, req *model.LLMRequest, cfg *model.GenerateConfig, stream bool) iter.Seq2[*model.LLMResponse, error]
GenerateContent sends the request to the Gemini GenerateContent API. When stream is false, exactly one complete *model.LLMResponse is yielded. When stream is true, partial text/reasoning chunks are yielded (Partial=true) followed by the assembled complete response (Partial=false, TurnComplete=true). Transient errors are automatically retried according to the retry.Config provided at construction time.
func (*GenerateContent) Name ¶
func (g *GenerateContent) Name() string
Name returns the model identifier.
type Option ¶ added in v0.0.7
type Option func(*GenerateContent)
Option configures a Gemini GenerateContent adapter.
func WithBaseURL ¶ added in v0.0.8
WithBaseURL overrides the Gemini or Vertex AI API endpoint for this adapter.
func WithRetryConfig ¶ added in v0.0.7
WithRetryConfig sets the retry behavior for transient API errors.
func WithThinkingEnabled ¶ added in v0.0.7
WithThinkingEnabled explicitly enables or disables Gemini thinking.
func WithThinkingLevel ¶ added in v0.0.7
func WithThinkingLevel(level ThinkingLevel) Option
WithThinkingLevel sets Gemini thinking depth for every call.
type ThinkingLevel ¶ added in v0.0.7
type ThinkingLevel string
ThinkingLevel controls Gemini thinking depth.
const ( // ThinkingLevelMinimal requests minimal Gemini thinking depth. ThinkingLevelMinimal ThinkingLevel = "minimal" // ThinkingLevelLow requests low Gemini thinking depth. ThinkingLevelLow ThinkingLevel = "low" // ThinkingLevelMedium requests medium Gemini thinking depth. ThinkingLevelMedium ThinkingLevel = "medium" // ThinkingLevelHigh requests high Gemini thinking depth. ThinkingLevelHigh ThinkingLevel = "high" )
Source Files