Enum Embedder

pub enum Embedder {
    HuggingFace(Embedder),
    OpenAi(Embedder),
    UserProvided(Embedder),
    Ollama(Embedder),
    Rest(Embedder),
    Composite(Embedder),
}

An embedder can be used to transform text into embeddings.

Variants

HuggingFace(Embedder)

An embedder based on running local models, fetched from the Hugging Face Hub.

OpenAi(Embedder)

An embedder based on making embedding queries against the OpenAI API.

UserProvided(Embedder)

An embedder based on the user providing the embeddings in the documents and queries.

Ollama(Embedder)

An embedder based on making embedding queries against an https://ollama.com embedding server.

Rest(Embedder)

An embedder based on making embedding queries against a generic JSON/REST embedding server.

Composite(Embedder)

An embedder composed of an embedder at search time and an embedder at indexing time.

Implementations

impl Embedder

pub fn new( options: EmbedderOptions, cache_cap: usize, ) -> Result<Self, NewEmbedderError>

Spawns a new embedder built from its options.

pub fn embed_search( &self, text: &str, deadline: Option<Instant>, ) -> Result<Embedding, EmbedError>

Embed in search context

pub fn embed_index( &self, text_chunks: Vec<Vec<String>>, threads: &ThreadPoolNoAbort, ) -> Result<Vec<Vec<Embedding>>, EmbedError>

Embed multiple chunks of texts.

Each chunk is composed of one or multiple texts.

pub fn embed_index_ref( &self, texts: &[&str], threads: &ThreadPoolNoAbort, ) -> Result<Vec<Embedding>, EmbedError>

Non-owning variant of Self::embed_index.

pub fn chunk_count_hint(&self) -> usize

Indicates the preferred number of chunks to pass to [Self::embed_chunks]

pub fn prompt_count_in_chunk_hint(&self) -> usize

Indicates the preferred number of texts in a single chunk passed to [Self::embed]

pub fn dimensions(&self) -> usize

Indicates the dimensions of a single embedding produced by the embedder.

pub fn distribution(&self) -> Option<DistributionShift>

An optional distribution used to apply an affine transformation to the similarity score of a document.

pub fn uses_document_template(&self) -> bool

Trait Implementations

impl Debug for Embedder

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.