Struct ModellerConfig 

pub struct ModellerConfig {
    pub max_topics: usize,
    pub new_topic_threshold: f32,
    pub centroid_learning_rate: f32,
}

Configuration for SemanticTopicModeller.

Fields

max_topics: usize

Maximum number of distinct topics allowed. Default: 20.

new_topic_threshold: f32

If the maximum cosine similarity between an embedding and every existing topic centroid is below this threshold, a new topic is created. Default: 0.5.

centroid_learning_rate: f32

Learning rate for the online centroid update rule: centroid = (1 - lr) * centroid + lr * embedding. Default: 0.1.

Trait Implementations

impl Clone for ModellerConfig

fn clone(&self) -> ModellerConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModellerConfig

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

Formats the value using the given formatter.

impl Default for ModellerConfig

fn default() -> Self

Returns the “default value” for a type.