Struct DocumentChunk 

pub struct DocumentChunk {
    pub base: DataPoint,
    pub text: String,
    pub chunk_size: usize,
    pub chunk_index: usize,
    pub cut_type: String,
    pub document_id: Uuid,
    pub is_part_of: Option<Uuid>,
    pub contains: Vec<Value>,
}

A chunk of text extracted from a document during the cognify pipeline.

Extends DataPoint (via #[serde(flatten)]) following the same pattern used by Entity, EntityType, and EdgeType.

Python equivalent: cognee.infrastructure.engine.models.DataPoint subclass DocumentChunk with metadata = {"index_fields": ["text"]}.

Fields

base: DataPoint

Base data point fields (id, timestamps, metadata, type, etc.)

text: String

The chunk text content.

chunk_size: usize

Token count (word count by default).

chunk_index: usize

Sequential index within the parent document, starting at 0.

cut_type: String

How the chunk boundary was determined (e.g. “paragraph_end”, “sentence_end”).

document_id: Uuid

ID of the parent document this chunk belongs to (convenience field).

is_part_of: Option<Uuid>

Document ID for graph edge (mirrors Python’s is_part_of relationship).

contains: Vec<Value>

Entity refs populated during graph extraction (mirrors Python’s contains list).

Implementations

impl DocumentChunk

pub fn new( id: Uuid, text: String, chunk_size: usize, chunk_index: usize, cut_type: String, document_id: Uuid, ) -> Self

Create a new DocumentChunk with a deterministic ID.

Sets:

• base.data_type = "DocumentChunk"
• base.metadata["index_fields"] = ["text"]
• base.id = the provided deterministic UUID
• is_part_of = Some(document_id)
• contains = 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 HasDataPoint for DocumentChunk

fn data_point(&self) -> &DataPoint

Borrow the embedded DataPoint of this container.

fn data_point_mut(&mut self) -> &mut DataPoint

Mutably borrow the embedded DataPoint of this container.

fn for_each_child_mut(&mut self, _visit: &mut dyn FnMut(&mut dyn HasDataPoint))

Visit every owned child that itself implements HasDataPoint. Default: no children. Override on container types whose fields own (rather than reference by Uuid) another HasDataPoint.

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.