Struct ScoringWeights

pub struct ScoringWeights {
    pub similarity: f32,
    pub recency: f32,
    pub reward: f32,
    pub success: f32,
    pub region_match: f32,
}

Scoring weights for Bayesian retrieval ranking.

Each weight controls the contribution of a factor to the final score. Higher score = less relevant (distance-like). Factors are normalized to [0, 1] before weighting.

Fields

similarity: f32

Weight for semantic similarity (HNSW distance, normalized).

recency: f32

Weight for recency factor (1 - exp(-λ·age)).

reward: f32

Weight for reward (1 - reward, so higher reward = lower score).

success: f32

Weight for typed-edge success score (1 - P(success)).

region_match: f32

Weight for region match (0 if same region, 1 if different).

Implementations

impl ScoringWeights

pub fn balanced() -> Self

Create weights with all factors active at equal strength.

pub fn agent_memory() -> Self

Create weights optimized for agent memory retrieval.

Prioritizes reward and success over recency.

Trait Implementations

impl Clone for ScoringWeights

fn clone(&self) -> ScoringWeights

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for ScoringWeights

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

Formats the value using the given formatter.

impl Default for ScoringWeights

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ScoringWeights

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ScoringWeights

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

where __S: Serializer,

Serialize this value into the given Serde serializer.