Struct Document

pub struct Document {
    pub page_content: String,
    pub metadata: HashMap<String, Value>,
}

A document represents a piece of text with associated metadata

Fields

page_content: String

The text content of the document

metadata: HashMap<String, Value>

Metadata associated with the document

Implementations

impl Document

pub fn new(page_content: impl Into<String>) -> Self

Create a new document with the given content

pub fn new_with_metadata( page_content: impl Into<String>, metadata: HashMap<String, Value>, ) -> Self

Create a new document with content and metadata

pub fn add_metadata(&mut self, key: impl Into<String>, value: Value)

Add metadata to the document

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

Get metadata value by key

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

Get metadata value as a string

pub fn get_metadata_number(&self, key: &str) -> Option<f64>

Get metadata value as a number

pub fn get_metadata_bool(&self, key: &str) -> Option<bool>

Get metadata value as a boolean

pub fn has_metadata(&self, key: &str) -> bool

Check if the document has a specific metadata key

pub fn len(&self) -> usize

Get the length of the document content

pub fn is_empty(&self) -> bool

Check if the document is empty

pub fn split(&self, chunk_size: usize, overlap: usize) -> Vec<Document>

Split the document into chunks

pub fn join(documents: &[Document], separator: &str) -> Document

Join multiple documents into one

Trait Implementations

impl Clone for Document

fn clone(&self) -> Document

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Document

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Document

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Document

fn eq(&self, other: &Document) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serializable for Document

fn namespace() -> Vec<String>

Get the namespace for this serializable object

fn is_serializable() -> bool

Check if this object is serializable

fn to_json(&self) -> Result<String>

Serialize this object to JSON

fn to_json_pretty(&self) -> Result<String>

Serialize this object to a pretty-printed JSON string

fn from_json(json: &str) -> Result<Self>

where Self: Sized,

Deserialize this object from JSON

fn to_dict(&self) -> Result<HashMap<String, Value>>

Serialize this object to a dictionary (HashMap)

fn from_dict(dict: &HashMap<String, Value>) -> Result<Self>

where Self: Sized,

Deserialize this object from a dictionary (HashMap)

fn type_name() -> &'static str

Get the type name for this serializable object

impl Serialize for Document

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl ToDocument for Document

fn to_document(&self) -> Document

Convert this object to a document

impl StructuralPartialEq for Document