Struct AnnSearchStats 

pub struct AnnSearchStats {
    pub index_size: usize,
    pub dimension: usize,
    pub ef_search: usize,
    pub k_requested: usize,
    pub k_returned: usize,
    pub search_time_us: u64,
    pub estimated_recall: f32,
    pub is_approximate: bool,
}

Statistics from an ANN search operation.

These metrics help users understand the quality/speed tradeoff of approximate search.

Fields

index_size: usize

Total vectors in the HNSW index.

dimension: usize

Dimension of vectors.

ef_search: usize

ef parameter used for this search (higher = more accurate but slower).

k_requested: usize

Number of results requested (k).

k_returned: usize

Number of results returned.

search_time_us: u64

Search time in microseconds.

estimated_recall: f32

Estimated recall based on ef/k ratio.

Formula: min(1.0, 0.9 + 0.1 * log2(ef / k)) This is an empirical estimate; actual recall depends on data distribution.

is_approximate: bool

Whether this was an approximate (HNSW) or exact search.

Trait Implementations

impl Clone for AnnSearchStats

fn clone(&self) -> AnnSearchStats

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AnnSearchStats

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

Formats the value using the given formatter.

impl Default for AnnSearchStats

fn default() -> AnnSearchStats

Returns the “default value” for a type.

impl Serialize for AnnSearchStats

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

where __S: Serializer,

Serialize this value into the given Serde serializer.