Struct Bm25Index 

pub struct Bm25Index {
    pub type_marker: String,
    pub version: String,
    pub options: IndexOptions,
    pub doc_count: usize,
    pub avg_doc_length: f64,
    pub docs: HashMap<String, DocInfo>,
    pub terms: HashMap<String, TermInfo>,
}

BM25 index structure - fully JSON serializable

Fields

type_marker: String

Type marker for JSON identification

version: String

Version for future compatibility

options: IndexOptions

Index configuration

doc_count: usize

Total number of documents

avg_doc_length: f64

Average document length (in tokens)

docs: HashMap<String, DocInfo>

Document metadata: id -> DocInfo

terms: HashMap<String, TermInfo>

Inverted index: term -> TermInfo

Implementations

impl Bm25Index

pub fn new(options: IndexOptions) -> Self

Create a new empty index with the given options

pub fn build(docs: &[Value], options: IndexOptions) -> Self

Build an index from an array of documents

impl Bm25Index

pub fn search(&self, query: &str, top_k: usize) -> Vec<SearchResult>

Search the index

pub fn explain(&self, query: &str, doc_id: &str) -> Option<ScoreExplanation>

Explain scoring for a specific document

pub fn terms(&self) -> Vec<(String, usize)>

Get all indexed terms with their document frequencies

pub fn similar(&self, doc_id: &str, top_k: usize) -> Vec<SearchResult>

Find similar documents using term overlap

Trait Implementations

impl Clone for Bm25Index

fn clone(&self) -> Bm25Index

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Bm25Index

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Bm25Index

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Bm25Index

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

where __S: Serializer,

Serialize this value into the given Serde serializer.