Struct DeduplicationConfig 

pub struct DeduplicationConfig {
    pub similarity_threshold: f32,
    pub strategy: DeduplicationStrategy,
    pub batch_size: usize,
    pub use_cosine: bool,
}

Deduplication configuration

Fields

similarity_threshold: f32

Similarity threshold for considering vectors as duplicates (0.0-1.0) Higher values = more strict (only very similar vectors are duplicates)

strategy: DeduplicationStrategy

Strategy for which duplicate to keep

batch_size: usize

Batch size for processing

use_cosine: bool

Use cosine similarity (true) or euclidean distance (false)

Trait Implementations

impl Clone for DeduplicationConfig

fn clone(&self) -> DeduplicationConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DeduplicationConfig

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

Formats the value using the given formatter.

impl Default for DeduplicationConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for DeduplicationConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DeduplicationConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.