Struct Embedder 

pub struct Embedder {

    pub source: EmbedderSource,
    pub url: Option<String>,
    pub api_key: Option<String>,
    pub model: Option<String>,
    pub revision: Option<String>,
    pub pooling: Option<String>,
    pub document_template: Option<String>,
    pub document_template_max_bytes: Option<usize>,
    pub dimensions: Option<usize>,
    pub distribution: Option<EmbedderDistribution>,
    pub request: Option<Value>,
    pub response: Option<Value>,
    pub binary_quantized: Option<bool>,
    pub indexing_embedder: Option<Box<Embedder>>,
    pub search_embedder: Option<Box<Embedder>>,
    pub indexing_fragments: Option<HashMap<String, EmbedderFragment>>,
    pub search_fragments: Option<HashMap<String, EmbedderFragment>>,
}

Fields

source: EmbedderSource

The third-party tool that will generate embeddings from documents

url: Option<String>

The URL Meilisearch contacts when querying the embedder

api_key: Option<String>

Authentication token Meilisearch should send with each request to the embedder. If not present, Meilisearch will attempt to read it from environment variables

model: Option<String>

The model your embedder uses when generating vectors

revision: Option<String>

Model revision hash

pooling: Option<String>

Pooling method for Hugging Face embedders

document_template: Option<String>

Template defining the data Meilisearch sends to the embedder

document_template_max_bytes: Option<usize>

Maximum allowed size of rendered document template

dimensions: Option<usize>

Number of dimensions in the chosen model. If not supplied, Meilisearch tries to infer this value

distribution: Option<EmbedderDistribution>

Describes the natural distribution of search results.

request: Option<Value>

A JSON value representing the request Meilisearch makes to the remote embedder

response: Option<Value>

A JSON value representing the response Meilisearch expects from the remote embedder

binary_quantized: Option<bool>

Once set to true, irreversibly converts all vector dimensions to 1-bit values

indexing_embedder: Option<Box<Embedder>>

Configures embedder to vectorize documents during indexing (composite embedders only)

search_embedder: Option<Box<Embedder>>

Configures embedder to vectorize search queries (composite embedders only)

indexing_fragments: Option<HashMap<String, EmbedderFragment>>

Configures multimodal embedding generation at indexing time.

search_fragments: Option<HashMap<String, EmbedderFragment>>

Configures incoming media fragments for multimodal search queries.

Trait Implementations

impl Clone for Embedder

fn clone(&self) -> Embedder

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Embedder

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

Formats the value using the given formatter.

impl Default for Embedder

fn default() -> Embedder

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Embedder

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Embedder

fn eq(&self, other: &Embedder) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Embedder

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Embedder