knncolle_hnsw Namespace Reference

knncolle bindings for HNSW search. More...

Classes
struct	DistanceConfig
	Distance configuration for the HNSW index. More...
class	HnswBuilder
	Perform an approximate nearest neighbor search with HNSW. More...
struct	HnswOptions
	Options for HnswBuilder and HnswPrebuilt. More...
class	HnswPrebuilt
	Prebuilt index for an Hnsw search. More...
class	HnswSearcher
	Searcher on an Hnsw index. More...
class	ManhattanDistance
	Manhattan distance. More...
class	SquaredEuclideanDistance
	Squared Euclidean distance. More...

Functions
template<typename HnswData_ = float>
DistanceConfig< HnswData_ >	makeEuclideanDistanceConfig ()
template<typename HnswData_ = float>
DistanceConfig< HnswData_ >	makeManhattanDistanceConfig ()

Detailed Description

knncolle bindings for HNSW search.

Function Documentation

makeEuclideanDistanceConfig()

template<typename HnswData_ = float>

DistanceConfig< HnswData_ > knncolle_hnsw::makeEuclideanDistanceConfig

(

)

Template Parameters

HnswData_

Type of data in the HNSW index, usually floating-point.

Returns

Configuration for using Euclidean distances in the HNSW index. DistanceConfig::create is set to hnswlib::L2Space if HnswData_ = float, otherwise it is set to SquaredEuclideanDistance.

makeManhattanDistanceConfig()

template<typename HnswData_ = float>

DistanceConfig< HnswData_ > knncolle_hnsw::makeManhattanDistanceConfig

(

)

Template Parameters

HnswData_

Type of data in the HNSW index, usually floating-point.

Returns

Configuration for using Manhattan distances in the HNSW index.