Struct Chunk 

pub struct Chunk {
    pub id: Uuid,
    pub text: String,
    pub index: usize,
    pub start_char: usize,
    pub end_char: usize,
    pub token_count: Option<usize>,
    pub section: Option<String>,
    pub page: Option<usize>,
    pub embedding_ids: EmbeddingIds,
}

A chunk of text from a document.

Documents are split into chunks for embedding and retrieval. Each chunk maintains positional information and embedding references.

Example

use reasonkit::{Chunk, EmbeddingIds};
use uuid::Uuid;

let chunk = Chunk {
    id: Uuid::new_v4(),
    text: "This is a chunk of text...".to_string(),
    index: 0,
    start_char: 0,
    end_char: 26,
    token_count: Some(7),
    section: Some("Introduction".to_string()),
    page: Some(1),
    embedding_ids: EmbeddingIds::default(),
};

Fields

id: Uuid

Unique identifier for this chunk

text: String

The text content of the chunk

index: usize

Position index within the document

start_char: usize

Starting character position in the original document

end_char: usize

Ending character position in the original document

token_count: Option<usize>

Estimated token count for the chunk

section: Option<String>

Section or heading this chunk belongs to

page: Option<usize>

Page number (for paginated documents)

embedding_ids: EmbeddingIds

References to stored embeddings

Trait Implementations

impl Clone for Chunk

fn clone(&self) -> Chunk

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Chunk

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Chunk

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Chunk

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

where __S: Serializer,

Serialize this value into the given Serde serializer.