vertexai

Documentation

Index

• func DefineEmbedder(name string) ai.Embedder
• func DefineModel(name string, caps *ai.ModelCapabilities) (ai.Model, error)
• func Embedder(name string) ai.Embedder
• func Init(ctx context.Context, cfg *Config) error
• func IsDefinedEmbedder(name string) bool
• func IsDefinedModel(name string) bool
• func Model(name string) ai.Model
• type Config
• type EmbedOptions

Functions

func DefineEmbedder

func DefineEmbedder(name string) ai.Embedder

DefineEmbedder defines an embedder with a given name.

func DefineModel

func DefineModel(name string, caps *ai.ModelCapabilities) (ai.Model, error)

DefineModel defines an unknown model with the given name. The second argument describes the capability of the model. Use IsDefinedModel to determine if a model is already defined. After Init is called, only the known models are defined.

func Embedder

func Embedder(name string) ai.Embedder

Embedder returns the ai.Embedder with the given name. It returns nil if the embedder was not defined.

func Init

func Init(ctx context.Context, cfg *Config) error

Init initializes the plugin and all known models and embedders. After calling Init, you may call DefineModel and DefineEmbedder to create and register any additional generative models and embedders

func IsDefinedEmbedder

func IsDefinedEmbedder(name string) bool

IsDefinedEmbedder reports whether the named Embedder is defined by this plugin.

func IsDefinedModel

func IsDefinedModel(name string) bool

IsDefinedModel reports whether the named Model is defined by this plugin.

func Model

func Model(name string) ai.Model

Model returns the ai.Model with the given name. It returns nil if the model was not defined.

Types

type Config

type Config struct {
	// The cloud project to use for Vertex AI.
	// If empty, the values of the environment variables GCLOUD_PROJECT
	// and GOOGLE_CLOUD_PROJECT will be consulted, in that order.
	ProjectID string
	// The location of the Vertex AI service. The default is "us-central1".
	Location string
	// Options to the Vertex AI client.
	ClientOptions []option.ClientOption
}

Config is the configuration for the plugin.

type EmbedOptions

type EmbedOptions struct {
	// Document title.
	Title string `json:"title,omitempty"`
	// Task type: RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, and so forth.
	// See the Vertex AI text embedding docs.
	TaskType string `json:"task_type,omitempty"`
}

EmbedOptions are options for the Vertex AI embedder. Set ai.EmbedRequest.Options to a value of type *EmbedOptions.