openai

Documentation

Overview

Package openai implements the OpenAI text embedding backend.

Supports text-embedding-3-small (1536d), text-embedding-3-large (3072d), and text-embedding-ada-002 (1536d). All support MRL dimension truncation.

Index

• Constants
• func ModelInfos() []engine.ModelInfo
• type Config
• type Engine
  • func New(cfg Config) (*Engine, error)
  • func (e *Engine) Dimensions() int
  • func (e *Engine) Embed(ctx context.Context, req embed.Request) (embed.Result, error)
  • func (e *Engine) EmbedBatch(ctx context.Context, reqs []embed.Request) ([]embed.Result, error)
  • func (e *Engine) EmbedCapabilities() embed.Capability

Constants

const (
	DefaultModel      = "text-embedding-3-small"
	DefaultDimensions = 1536
)

Functions

func ModelInfos

func ModelInfos() []engine.ModelInfo

ModelInfos returns i18n metadata for OpenAI embedding models.

Types

type Config

type Config struct {
	APIKey     string
	BaseURL    string
	Model      string
	Dimensions int
	RPM        int
	HTTPClient *http.Client
}

Config configures the OpenAI embedding engine.

type Engine

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

Engine implements embed.EmbedEngine for OpenAI embeddings.

func New

func New(cfg Config) (*Engine, error)

New creates an OpenAI embedding engine.

func (*Engine) Dimensions

func (e *Engine) Dimensions() int

func (*Engine) Embed

func (e *Engine) Embed(ctx context.Context, req embed.Request) (embed.Result, error)

Embed produces a vector for text content.

func (*Engine) EmbedBatch

func (e *Engine) EmbedBatch(ctx context.Context, reqs []embed.Request) ([]embed.Result, error)

EmbedBatch embeds multiple texts in a single API call.

func (*Engine) EmbedCapabilities

func (e *Engine) EmbedCapabilities() embed.Capability

EmbedCapabilities implements embed.Describer.