Struct DocumentChunk 

pub struct DocumentChunk {
    pub document_id: String,
    pub content: String,
    pub chunk_index: usize,
    pub start_position: usize,
    pub end_position: usize,
    pub overlap_previous: usize,
    pub overlap_next: usize,
    pub metadata: Metadata,
}

Document chunk for processing pipelines

Represents a portion of a document with positional information and overlap handling for better context preservation.

Fields

document_id: String

Reference to parent document ID

content: String

Chunk content

chunk_index: usize

Chunk index within the document

start_position: usize

Character start position in original document

end_position: usize

Character end position in original document

overlap_previous: usize

Overlap with previous chunk (characters)

overlap_next: usize

Overlap with next chunk (characters)

metadata: Metadata

Chunk metadata (inherited from document + chunk-specific)

Implementations

impl DocumentChunk

pub fn new( document_id: impl Into<String>, content: impl Into<String>, chunk_index: usize, start_position: usize, end_position: usize, ) -> Self

Create a new document chunk

pub fn with_overlap(self, previous: usize, next: usize) -> Self

Set overlap information

pub fn with_metadata(self, key: impl Into<String>, value: Value) -> Self

Add metadata

pub fn length(&self) -> usize

Get chunk length

pub fn is_empty(&self) -> bool

Check if chunk is empty

Trait Implementations

impl Clone for DocumentChunk

fn clone(&self) -> DocumentChunk

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DocumentChunk

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DocumentChunk

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DocumentChunk

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

where __S: Serializer,

Serialize this value into the given Serde serializer.