Struct ChunkConfig 

pub struct ChunkConfig {
    pub max_tokens: usize,
    pub overlap_tokens: usize,
    pub min_tokens: usize,
    pub encoding: String,
    pub preserve_paragraphs: bool,
}

Chunker configuration.

Fields

max_tokens: usize

Hard cap on tokens per chunk.

overlap_tokens: usize

Number of trailing tokens of each chunk re-prepended to the next. Set to 0 to disable overlap.

min_tokens: usize

Drop chunks shorter than this.

encoding: String

Encoding name (cl100k_base or o200k_base).

preserve_paragraphs: bool

Treat blank-line-separated paragraphs as hard boundaries: never pack content from two paragraphs into the same chunk, even if the budget allows it. Default: false (the historical behavior). Useful for documents with semantically distinct sections.

Trait Implementations

impl Clone for ChunkConfig

fn clone(&self) -> ChunkConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChunkConfig

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

Formats the value using the given formatter.

impl Default for ChunkConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChunkConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ChunkConfig

fn eq(&self, other: &ChunkConfig) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ChunkConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for ChunkConfig

impl StructuralPartialEq for ChunkConfig