Struct DocumentConfig 

pub struct DocumentConfig {
    pub chunk_chars: usize,
    pub overlap_chars: usize,
    pub min_chunk_chars: usize,
    pub max_chunk_chars: usize,
    pub max_overlap_ratio: f32,
    pub max_chunks: usize,
    pub sentence_terminators: Vec<char>,
}

How documents are split into chunks.

Fields

chunk_chars: usize

Target chunk length in characters.

overlap_chars: usize

Characters carried from the end of one chunk to the start of the next.

min_chunk_chars: usize

Smallest chunk_chars a request may ask for.

max_chunk_chars: usize

Largest chunk_chars a request may ask for.

max_overlap_ratio: f32

Largest overlap as a fraction of the chunk length.

max_chunks: usize

Most chunks one document may produce.

sentence_terminators: Vec<char>

Characters that end a sentence when a paragraph must be split.

Trait Implementations

impl Clone for DocumentConfig

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DocumentConfig

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

Formats the value using the given formatter.

impl Default for DocumentConfig

fn default() -> Self

Returns the “default value” for a type.