Struct Document 

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

Class for storing a piece of text and associated metadata.

Document is for retrieval workflows, not chat I/O. For sending text to an LLM in a conversation, use message types from the messages module.

Example

use agent_chain_core::documents::Document;
use std::collections::HashMap;

let document = Document::new("Hello, world!")
    .with_metadata(HashMap::from([
        ("source".to_string(), serde_json::json!("https://example.com"))
    ]));

Fields

page_content: String

String text content of the document.

id: Option<String>

An optional identifier for the document.

Ideally this should be unique across the document collection and formatted as a UUID, but this will not be enforced.

metadata: HashMap<String, Value>

Arbitrary metadata associated with the content.

type_: String

Type identifier, always “Document”.

Implementations

impl Document

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

Create a new Document with the given page content.

pub fn with_id(self, id: impl Into<String>) -> Self

Set the ID.

pub fn with_metadata(self, metadata: HashMap<String, Value>) -> Self

Set the metadata.

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

Add a single metadata entry.

pub fn content(&self) -> &str

Get the page content as a string reference.

pub fn is_empty(&self) -> bool

Check if the document is empty.

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 Display for Document

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

Formats the value using the given formatter.

impl From<&str> for Document

fn from(s: &str) -> Self

Converts to this type from the input type.

impl From<String> for Document

fn from(s: String) -> Self

Converts to this type from the input type.

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 is_lc_serializable() -> bool

where Self: Sized,

Is this class serializable?

fn get_lc_namespace() -> Vec<String>

where Self: Sized,

Get the namespace of the LangChain object.

fn lc_secrets(&self) -> HashMap<String, String>

A map of constructor argument names to secret ids.

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

List of attribute names that should be included in the serialized kwargs.

fn lc_id() -> Vec<String>

where Self: Sized,

Return a unique identifier for this class for serialization purposes.

fn lc_type_name(&self) -> &'static str

Get the type name of this object.

fn to_json(&self) -> Serialized

where Self: Sized + Serialize,

Serialize this object to JSON.

fn to_json_not_implemented(&self) -> Serialized

Serialize a “not implemented” 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 StructuralPartialEq for Document