embed

package
v1.9.27 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Nov 27, 2025 License: Apache-2.0 Imports: 6 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type Embedder

type Embedder struct {
	// contains filtered or unexported fields
}

Embedder generates vector embeddings for text

func New

func New(p provider.Provider, opts ...Option) *Embedder

New creates a new embedder using a model provider with optional configuration

func (*Embedder) Embed

func (e *Embedder) Embed(ctx context.Context, text string) ([]float64, error)

Embed generates an embedding for a single text Emits usage event immediately via handler if set

func (*Embedder) EmbedBatch

func (e *Embedder) EmbedBatch(ctx context.Context, texts []string) ([][]float64, error)

EmbedBatch generates embeddings for multiple texts using intelligent batching If the provider supports batch embeddings, it will use parallel batch API calls Otherwise, it falls back to sequential processing

func (*Embedder) SetUsageHandler

func (e *Embedder) SetUsageHandler(handler func(tokens int, cost float64))

SetUsageHandler sets a callback to be called after each embedding with usage info

type Option

type Option func(*Embedder)

Option is a functional option for configuring the Embedder

func WithBatchSize

func WithBatchSize(size int) Option

WithBatchSize sets the batch size for embedding API calls (default: 50)

func WithMaxConcurrency

func WithMaxConcurrency(maxConcurrency int) Option

WithMaxConcurrency sets the maximum concurrent embedding batch requests (default: 5)

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL