Struct BM25Index 

pub struct BM25Index { /* private fields */ }

BM25 index implementation

Implementations

impl BM25Index

pub fn to_compressed_bytes(&self, compression: Compression) -> Result<Vec<u8>>

Serialize to compressed bytes using specified compression

Errors

Returns error if serialization or compression fails

pub fn from_compressed_bytes( data: &[u8], compression: Compression, ) -> Result<Self>

Deserialize from compressed bytes

Errors

Returns error if decompression or deserialization fails

impl BM25Index

pub fn new() -> Self

Create a new BM25 index with default parameters

pub fn with_params(k1: f32, b: f32) -> Self

Create with custom BM25 parameters

pub fn with_stopwords(self, stopwords: HashSet<String>) -> Self

Set stopwords

pub fn tokenize(&self, text: &str) -> Vec<String>

Tokenize text

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 Default for BM25Index

fn default() -> Self

Returns the “default value” for a type.

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.

impl SparseIndex for BM25Index

fn add(&mut self, chunk: &Chunk)

Index a chunk

fn add_batch(&mut self, chunks: &[Chunk])

Index multiple chunks

fn search(&self, query: &str, k: usize) -> Vec<(ChunkId, f32)>

Search for matching chunks

fn remove(&mut self, chunk_id: ChunkId)

Remove a chunk from the index

fn len(&self) -> usize

Get the number of indexed documents

fn is_empty(&self) -> bool

Check if the index is empty