Enum RecallStrategy 

pub enum RecallStrategy {
    Balanced,
    Semantic,
    Lexical,
    Recent,
    Relational,
}

How recall should weight its retrieval signals.

Variants

Balanced

Even blend of semantic and lexical signals with mild recency.

Semantic

Meaning-first: lean on the vector index.

Lexical

Exact-term-first: lean on BM25.

Recent

Recency-first: what happened lately matters most.

Relational

Relation-first: follow entity links — “things connected to X”, not just “things similar to X”.

Implementations

impl RecallStrategy

pub fn weights(self) -> (f32, f32, f32, f32)

(vector_weight, lexical_weight, graph_weight, recency_weight)

Trait Implementations

impl Clone for RecallStrategy

fn clone(&self) -> RecallStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for RecallStrategy

impl Debug for RecallStrategy

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

Formats the value using the given formatter.

impl Default for RecallStrategy

fn default() -> RecallStrategy

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for RecallStrategy

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for RecallStrategy

impl PartialEq for RecallStrategy

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for RecallStrategy

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 RecallStrategy