Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Embedder ¶
type Embedder interface {
// Embed returns a vector embedding for the given text.
Embed(ctx context.Context, text string) ([]float32, error)
// EmbedBatch returns vector embeddings for multiple texts.
EmbedBatch(ctx context.Context, texts []string) ([][]float32, error)
// Dimension returns the embedding vector dimension.
Dimension() int
}
Embedder generates vector embeddings from text.
func New ¶ added in v0.10.0
func New(ollaCfg config.OllamaConfig, embCfg config.EmbedderConfig, dimension int, logger *slog.Logger) (Embedder, error)
New returns an Embedder implementation selected by embCfg.Provider.
Supported providers:
- "" or "ollama" → OllamaEmbedder using ollaCfg
- "lmstudio" → LMStudioEmbedder using embCfg.LMStudio
Any other provider string is an error.
type LMStudioEmbedder ¶ added in v0.10.0
type LMStudioEmbedder struct {
// contains filtered or unexported fields
}
LMStudioEmbedder implements Embedder using the LM Studio local server's OpenAI-compatible /v1/embeddings endpoint.
func NewLMStudioEmbedder ¶ added in v0.10.0
func NewLMStudioEmbedder(baseURL, model string) *LMStudioEmbedder
NewLMStudioEmbedder creates a new LM Studio embedder pointed at baseURL using the given model name.
func (*LMStudioEmbedder) Dimension ¶ added in v0.10.0
func (e *LMStudioEmbedder) Dimension() int
Dimension returns 0 — LM Studio does not report dimension at construction time; callers should use the length of the returned slice from Embed.
func (*LMStudioEmbedder) Embed ¶ added in v0.10.0
Embed returns a vector embedding for the given text by calling the LM Studio /v1/embeddings endpoint.
func (*LMStudioEmbedder) EmbedBatch ¶ added in v0.10.0
EmbedBatch returns embeddings for multiple texts by calling Embed in a loop.
type OllamaEmbedder ¶
type OllamaEmbedder struct {
// contains filtered or unexported fields
}
OllamaEmbedder implements Embedder using the Ollama HTTP API.
func NewOllamaEmbedder ¶
func NewOllamaEmbedder(baseURL, model string, dimension int, logger *slog.Logger) *OllamaEmbedder
NewOllamaEmbedder creates a new Ollama-based embedder.
func (*OllamaEmbedder) Dimension ¶
func (o *OllamaEmbedder) Dimension() int
Dimension returns the embedding vector dimension.
func (*OllamaEmbedder) Embed ¶
Embed returns a vector embedding for the given text using the Ollama API.
func (*OllamaEmbedder) EmbedBatch ¶
EmbedBatch embeds multiple texts in a single HTTP call to Ollama's /api/embed endpoint, which accepts an array of inputs and returns all embeddings at once. This is dramatically faster than per-text calls (1 round-trip vs N).
Source Files