Struct ModelConfig 

pub struct ModelConfig {
    pub model: EmbeddingModel,
    pub name: &'static str,
    pub hf_repo: &'static str,
    pub onnx_path: &'static str,
    pub vocab_file: VocabSource,
    pub dimensions: usize,
    pub max_seq_len: usize,
    pub model_min_bytes: u64,
    pub vocab_min_bytes: u64,
    pub query_prefix: Option<&'static str>,
    pub document_prefix: Option<&'static str>,
    pub needs_token_type_ids: bool,
}

Complete configuration for a single embedding model.

Fields

model: EmbeddingModel

name: &'static str

hf_repo: &'static str

onnx_path: &'static str

vocab_file: VocabSource

dimensions: usize

max_seq_len: usize

model_min_bytes: u64

vocab_min_bytes: u64

query_prefix: Option<&'static str>

Optional prefix prepended to queries before embedding.

document_prefix: Option<&'static str>

Optional prefix prepended to documents/code before embedding.

needs_token_type_ids: bool

Whether the model expects token_type_ids input (BERT-style). Some models (e.g. nomic-embed) only use input_ids + attention_mask.

Implementations

impl ModelConfig

pub fn model_url(&self) -> String

Full HuggingFace download URL for the ONNX model file.

pub fn vocab_url(&self) -> String

Full HuggingFace download URL for the vocabulary/tokenizer file.

Trait Implementations

impl Clone for ModelConfig

fn clone(&self) -> ModelConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelConfig

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

Formats the value using the given formatter.