Enum ChunkingStrategy 

pub enum ChunkingStrategy {
    FixedSize {
        chunk_size: usize,
        overlap: usize,
    },
    Paragraph,
    Sentence,
    Semantic {
        max_chunk_tokens: usize,
    },
}

Strategy for splitting documents into chunks.

Variants

FixedSize

Fixed-size chunks measured in characters, with optional overlap.

Fields

chunk_size: usize

Maximum number of characters per chunk.

overlap: usize

Number of overlapping characters between consecutive chunks.

Paragraph

Split on paragraph boundaries (double newlines).

Sentence

Split on sentence boundaries (. / ! / ? followed by whitespace).

Semantic

Split on heading boundaries (lines starting with #), with a maximum token budget per chunk.

Fields

max_chunk_tokens: usize

Maximum estimated tokens per chunk.

Trait Implementations

impl Clone for ChunkingStrategy

fn clone(&self) -> ChunkingStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChunkingStrategy

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ChunkingStrategy

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ChunkingStrategy

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

where __S: Serializer,

Serialize this value into the given Serde serializer.