openai

Documentation

Index

• type Embedder
  • func New(client *openai.Client, opts ...embedder.Option) *Embedder
  • func (p *Embedder) BatchEmbed(ctx context.Context, parts []string, usage *components.LLMUsage) ([]embedder.Embedding, error)
  • func (p *Embedder) DotProduct(ctx context.Context, target, query *embedder.Embedding) (float64, error)
  • func (p *Embedder) Embed(ctx context.Context, text string, embedding *embedder.Embedding, ...) error
  • func (p *Embedder) SetClient(clt *openai.Client)

Types

type Embedder

type Embedder struct {
	*openai.Client

	embedder.Options
}

func New

func New(client *openai.Client, opts ...embedder.Option) *Embedder

func (*Embedder) BatchEmbed

func (p *Embedder) BatchEmbed(ctx context.Context, parts []string, usage *components.LLMUsage) ([]embedder.Embedding, error)

func (*Embedder) DotProduct

func (p *Embedder) DotProduct(ctx context.Context, target, query *embedder.Embedding) (float64, error)

DotProduct calculates the dot product of the embedding vector with another embedding vector. Both vectors must have the same length; otherwise, an ErrVectorLengthMismatch is returned. The method returns the calculated dot product as a float32 value.

func (*Embedder) Embed

func (p *Embedder) Embed(ctx context.Context, text string, embedding *embedder.Embedding, usage *components.LLMUsage) error

func (*Embedder) SetClient

func (p *Embedder) SetClient(clt *openai.Client)