Enum CrossEncoder 

pub enum CrossEncoder {
    Lexical,
    Neural {
        model: Arc<Mutex<BertModel>>,
        tokenizer: Arc<Tokenizer>,
        classifier_weight: Tensor,
        classifier_bias: Tensor,
        device: Device,
    },
}

Cross-encoder for (query, document) relevance scoring.

Variants

Lexical

Lightweight lexical cross-encoder using term overlap signals.

Neural

Neural BERT-based cross-encoder (ms-marco-MiniLM-L-6-v2).

Fields

model: Arc<Mutex<BertModel>>

tokenizer: Arc<Tokenizer>

classifier_weight: Tensor

classifier_bias: Tensor

device: Device

Implementations

impl CrossEncoder

pub fn new() -> Self

Create a new lexical cross-encoder (no model download required).

pub fn new_neural() -> Self

Create a neural cross-encoder by downloading ms-marco-MiniLM-L-6-v2.

Falls back to lexical if download or loading fails.

v0.6.3.1 (P3, G8): when the neural path fails (e.g. HF Hub unreachable, model checksum mismatch), emit a structured tracing event reranker.fallback so operators see the silent neural→lexical degrade. The eprintln remains for backward-compat startup logs.

pub fn score(&self, query: &str, title: &str, content: &str) -> f32

Score a single (query, document) pair.

Returns a relevance score in 0.0..=1.0.

pub fn is_neural(&self) -> bool

Whether this is a neural cross-encoder.

pub fn rerank( &self, query: &str, candidates: Vec<(Memory, f64)>, ) -> Vec<(Memory, f64)>

Rerank a set of candidates by blending their original scores with cross-encoder scores.

Blend formula: final = 0.6 * original + 0.4 * cross_encoder

Results are returned sorted by final_score descending.

Trait Implementations

impl Default for CrossEncoder

fn default() -> Self

Returns the “default value” for a type.