Struct LateChunkingConfig 

pub struct LateChunkingConfig {
    pub chunk_size: usize,
    pub chunk_overlap: usize,
    pub max_doc_tokens: u32,
    pub annotate_positions: bool,
}

Configuration for the late chunking strategy

Fields

chunk_size: usize

Target chunk size in characters

chunk_overlap: usize

Chunk overlap in characters

max_doc_tokens: u32

Maximum document size in tokens before splitting into sections.

• 8192 for Jina v3 (default)
• 32768 for gte-Qwen2-7B-instruct

annotate_positions: bool

Annotate each chunk’s position_in_document metadata field.

Embedding providers can use this to apply position-aware pooling.

Trait Implementations

impl Clone for LateChunkingConfig

fn clone(&self) -> LateChunkingConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LateChunkingConfig

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

Formats the value using the given formatter.

impl Default for LateChunkingConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LateChunkingConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LateChunkingConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.