Struct ConceptExtractionConfig 

pub struct ConceptExtractionConfig {
    pub min_concept_length: usize,
    pub max_concept_words: usize,
    pub use_noun_phrases: bool,
    pub use_capitalization: bool,
    pub use_title_case: bool,
    pub use_tf_idf_scoring: bool,
    pub min_term_frequency: usize,
    pub max_concepts_per_chunk: usize,
    pub min_concept_score: f32,
    pub exclude_stopwords: bool,
    pub custom_stopwords: Vec<String>,
}

Configuration for extracting concepts from text documents. This configuration controls how key concepts are identified and extracted from text.

Fields

min_concept_length: usize

Minimum length of a concept in characters

max_concept_words: usize

Maximum number of words in a multi-word concept

use_noun_phrases: bool

Whether to extract noun phrases as concepts

use_capitalization: bool

Whether to consider capitalized words as potential concepts

use_title_case: bool

Whether to consider title-cased phrases as potential concepts

use_tf_idf_scoring: bool

Whether to use TF-IDF scoring for concept importance

min_term_frequency: usize

Minimum term frequency for a term to be considered a concept

max_concepts_per_chunk: usize

Maximum number of concepts to extract per document chunk

min_concept_score: f32

Minimum score threshold for a term to be considered a concept

exclude_stopwords: bool

Whether to exclude common stopwords from concept extraction

custom_stopwords: Vec<String>

Custom list of stopwords to exclude from concept extraction

Trait Implementations

impl Clone for ConceptExtractionConfig

fn clone(&self) -> ConceptExtractionConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ConceptExtractionConfig

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

Formats the value using the given formatter.

impl Default for ConceptExtractionConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ConceptExtractionConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ConceptExtractionConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.