Struct TextChunk 

pub struct TextChunk {
    pub id: ChunkId,
    pub document_id: DocumentId,
    pub content: String,
    pub start_offset: usize,
    pub end_offset: usize,
    pub embedding: Option<Vec<f32>>,
    pub entities: Vec<EntityId>,
    pub metadata: ChunkMetadata,
}

A chunk of text from a document

Fields

id: ChunkId

Unique identifier for the chunk

document_id: DocumentId

ID of the parent document

content: String

Text content of the chunk

start_offset: usize

Starting character offset in the original document

end_offset: usize

Ending character offset in the original document

embedding: Option<Vec<f32>>

Optional vector embedding for the chunk

entities: Vec<EntityId>

List of entity IDs mentioned in this chunk

metadata: ChunkMetadata

Semantic metadata for the chunk (chapter, keywords, summary, etc.)

Implementations

impl TextChunk

pub fn new( id: ChunkId, document_id: DocumentId, content: String, start_offset: usize, end_offset: usize, ) -> Self

Create a new text chunk

pub fn with_embedding(self, embedding: Vec<f32>) -> Self

Add an embedding to the chunk

pub fn with_entities(self, entities: Vec<EntityId>) -> Self

Add entities to the chunk

pub fn with_metadata(self, metadata: ChunkMetadata) -> Self

Add metadata to the chunk

Trait Implementations

impl Clone for TextChunk

fn clone(&self) -> TextChunk

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TextChunk

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for TextChunk

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TextChunk

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

where __S: Serializer,

Serialize this value into the given Serde serializer.