Struct DocumentChunk 

pub struct DocumentChunk {
    pub id: String,
    pub content: String,
    pub metadata: HashMap<String, String>,
    pub embedding: Vec<f32>,
    pub document_id: String,
    pub position: usize,
    pub length: usize,
}

Document chunk for processing

Fields

id: String

Unique chunk ID

content: String

Chunk content

metadata: HashMap<String, String>

Chunk metadata

embedding: Vec<f32>

Embedding vector

document_id: String

Source document ID

position: usize

Chunk position in document

length: usize

Chunk length

Implementations

impl DocumentChunk

pub fn new( id: String, content: String, metadata: HashMap<String, String>, embedding: Vec<f32>, document_id: String, position: usize, length: usize, ) -> Self

Create a new document chunk

pub fn size(&self) -> usize

Get chunk size

pub fn is_empty(&self) -> bool

Check if chunk is empty

pub fn get_metadata(&self, key: &str) -> Option<&String>

Get metadata value

pub fn set_metadata(&mut self, key: String, value: String)

Set metadata value

pub fn similarity(&self, other: &DocumentChunk) -> f32

Calculate similarity with another chunk

pub fn preview(&self) -> String

Get content preview (first 100 characters)

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.