Struct Document 

pub struct Document {
    pub id: Uuid,
    pub doc_type: DocumentType,
    pub source: Source,
    pub content: DocumentContent,
    pub metadata: Metadata,
    pub processing: ProcessingStatus,
    pub chunks: Vec<Chunk>,
    pub created_at: DateTime<Utc>,
    pub updated_at: Option<DateTime<Utc>>,
}

A document in the knowledge base.

The primary data structure for storing and managing documents. Contains content, metadata, processing status, and chunks.

Example

use reasonkit::{Document, DocumentType, Source, SourceType};
use chrono::Utc;

let source = Source {
    source_type: SourceType::Local,
    url: None,
    path: Some("/path/to/doc.md".to_string()),
    arxiv_id: None,
    github_repo: None,
    retrieved_at: Utc::now(),
    version: None,
};

let doc = Document::new(DocumentType::Documentation, source)
    .with_content("# My Document\n\nContent here...".to_string());

assert_eq!(doc.doc_type, DocumentType::Documentation);
assert!(doc.content.word_count > 0);

Fields

id: Uuid

Unique document identifier

doc_type: DocumentType

Document type categorization

source: Source

Source information for provenance

content: DocumentContent

Document content

metadata: Metadata

Document metadata

processing: ProcessingStatus

Processing status

chunks: Vec<Chunk>

Text chunks for retrieval

created_at: DateTime<Utc>

Creation timestamp

updated_at: Option<DateTime<Utc>>

Last update timestamp

Implementations

impl Document

pub fn new(doc_type: DocumentType, source: Source) -> Self

Create a new document with the given type and source.

Arguments

• doc_type - The type of document
• source - Source information for provenance

Example

use reasonkit::{Document, DocumentType, Source, SourceType};
use chrono::Utc;

let source = Source {
    source_type: SourceType::Local,
    url: None,
    path: Some("/path/to/file.txt".to_string()),
    arxiv_id: None,
    github_repo: None,
    retrieved_at: Utc::now(),
    version: None,
};

let doc = Document::new(DocumentType::Note, source);
assert_eq!(doc.doc_type, DocumentType::Note);

pub fn with_content(self, raw: String) -> Self

Set the document content and compute statistics.

Arguments

• raw - The raw content string

Example

use reasonkit::{Document, DocumentType, Source, SourceType};
use chrono::Utc;

let source = Source {
    source_type: SourceType::Local,
    url: None,
    path: None,
    arxiv_id: None,
    github_repo: None,
    retrieved_at: Utc::now(),
    version: None,
};

let doc = Document::new(DocumentType::Note, source)
    .with_content("Hello world".to_string());

assert_eq!(doc.content.word_count, 2);
assert_eq!(doc.content.char_count, 11);

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

Set the document metadata.

Arguments

• metadata - The metadata to set

Example

use reasonkit::{Document, DocumentType, Source, SourceType, Metadata};
use chrono::Utc;

let source = Source {
    source_type: SourceType::Local,
    url: None,
    path: None,
    arxiv_id: None,
    github_repo: None,
    retrieved_at: Utc::now(),
    version: None,
};

let metadata = Metadata {
    title: Some("My Document".to_string()),
    ..Default::default()
};

let doc = Document::new(DocumentType::Note, source)
    .with_metadata(metadata);

assert_eq!(doc.metadata.title, Some("My Document".to_string()));

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 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.