jina

Documentation

Overview

Package jina implements the Jina AI embedding backend.

Supports jina-clip-v2 (multimodal: text + image, 1024d), jina-embeddings-v3 (text-only, 1024d with MRL).

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      = "jina-clip-v2"
	DefaultDimensions = 1024
)

Functions

func ModelInfos

func ModelInfos() []engine.ModelInfo

ModelInfos returns i18n metadata for Jina embedding models.

Types

type Config

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

Config configures the Jina embedding engine.

type Engine

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

Engine implements embed.EmbedEngine for Jina AI.

func New

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

New creates a Jina 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 or image content. Jina CLIP v2 supports both text and image in a unified vector space.

func (*Engine) EmbedBatch

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

EmbedBatch embeds multiple requests sequentially.

func (*Engine) EmbedCapabilities

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

EmbedCapabilities implements embed.Describer.