Enum AggregationMethod 

pub enum AggregationMethod {
    Max,
    Mean,
    First,
    Last,
    Sum,
}

Aggregation method for multi-vector documents

Variants

Max

Use the maximum score across all chunks (recommended for most use cases) This is equivalent to “did any chunk match well?”

Mean

Use the average score across all chunks Good for measuring overall document relevance

First

Use the score of the first chunk Good for documents where order matters (e.g., abstracts first)

Last

Use the score of the last chunk

Sum

Sum of all chunk scores (for sparse-like behavior)

Implementations

impl AggregationMethod

pub fn from_str(s: &str) -> Option<Self>

Parse from string

Trait Implementations

impl Clone for AggregationMethod

fn clone(&self) -> AggregationMethod

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for AggregationMethod

impl Debug for AggregationMethod

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

Formats the value using the given formatter.

impl Default for AggregationMethod

fn default() -> AggregationMethod

Returns the “default value” for a type.

impl Eq for AggregationMethod

impl PartialEq for AggregationMethod

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for AggregationMethod