Struct ExtractionConfig 

#[non_exhaustive]
pub struct ExtractionConfig {
    pub context_window: usize,
    pub dedup_enabled: bool,
    pub max_passage_sentences: usize,
}

Configuration for passage extraction around high-recurrence terms.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

context_window: usize

Number of surrounding sentences to include on each side.

dedup_enabled: bool

Whether to deduplicate extracted passages by content hash.

max_passage_sentences: usize

Maximum number of sentences allowed in a single extracted passage.

If a merged range exceeds this value, it is split into sentence-boundary chunks of at most this size. A value of 0 is treated as a per-sentence cap (each sentence becomes its own chunk).

After splitting, each chunk is re-evaluated and chunks that do not contain any matching high-recurrence term are discarded. As a result, when context_window is larger than max_passage_sentences, some context-only sentences may be dropped and the effective surrounding context in the returned passages can be smaller than the original merged window.

Trait Implementations

impl Clone for ExtractionConfig

fn clone(&self) -> ExtractionConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExtractionConfig

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

Formats the value using the given formatter.

impl Default for ExtractionConfig

fn default() -> Self

Returns the “default value” for a type.