Struct Document 

pub struct Document {

    pub id: String,
    pub url: String,
    pub title: String,
    pub body: String,
    pub description: Option<String>,
    pub summarization: Option<String>,
    pub stub: Option<String>,
    pub tags: Option<Vec<String>>,
    pub rank: Option<u64>,
    pub source_haystack: Option<String>,
    pub doc_type: DocumentType,
    pub synonyms: Option<Vec<String>>,
    pub route: Option<RouteDirective>,
    pub priority: Option<u8>,
}

The central document type representing indexed and searchable content.

Documents are the primary unit of content in Terraphim. They can come from various sources (local files, web pages, API responses) and are indexed for semantic search using knowledge graphs.

Fields

• id - Unique identifier (typically a UUID or URL-based ID)
• url - Source URL or file path
• title - Document title (used for display and basic search)
• body - Full text content
• description - Optional short description (extracted or provided)
• summarization - Optional AI-generated summary
• stub - Optional brief excerpt
• tags - Optional categorization tags (often from knowledge graph)
• rank - Optional relevance score from search results
• source_haystack - Optional identifier of the data source that provided this document

Examples

use terraphim_types::{Document, DocumentType};

let doc = Document {
    id: "rust-book-ch1".to_string(),
    url: "https://doc.rust-lang.org/book/ch01-00-getting-started.html".to_string(),
    title: "Getting Started".to_string(),
    body: "Let's start your Rust journey...".to_string(),
    description: Some("Introduction to Rust programming".to_string()),
    summarization: None,
    stub: None,
    tags: Some(vec!["rust".to_string(), "tutorial".to_string()]),
    rank: Some(95),
    source_haystack: Some("rust-docs".to_string()),
    doc_type: DocumentType::KgEntry,
    synonyms: None,
    route: None,
    priority: None,
};

Fields

id: String

Unique identifier for the document

url: String

URL to the document

title: String

Title of the document

body: String

The document body

description: Option<String>

A short description of the document (extracted from content)

summarization: Option<String>

AI-generated summarization of the document content

stub: Option<String>

A short excerpt of the document

tags: Option<Vec<String>>

Tags for the document

rank: Option<u64>

Rank of the document in the search results

source_haystack: Option<String>

Source haystack location that this document came from

doc_type: DocumentType

Document classification derived from directives

synonyms: Option<Vec<String>>

Synonyms extracted from directives (optional)

route: Option<RouteDirective>

Optional route directive (provider/model)

priority: Option<u8>

Optional priority directive (0-100)

Implementations

impl Document

pub fn with_source_haystack(self, haystack_location: String) -> Self

Set the source haystack for this document

pub fn get_source_haystack(&self) -> Option<&String>

Get the source haystack location

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 Default for Document

fn default() -> Document

Returns the “default value” for a type.

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 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.