HNSWGO

This is a golang binding of hnswlib. For more information, please follow hnswlib and Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs..

Build

CGO is required to be enabled and c, c++ compiler is required to build this package.

go get github.com/oligo/hnswgo

Usage and config

See example/example.go or test codes to see usage. For detailed information, please refer to the project's documentation at pkg.go.dev.

Some important arguments are listed below:

argument	type
dim	int	vector dimension
M	int	seeALGO_PARAMS.md
efConstruction	int	seeALGO_PARAMS.md
randomSeed	int	random seed for hnsw
maxElements	int	max records in data
spaceType	str

spaceType	distance
ip	inner product
cosine	cosine similarity
l2	l2

HNSWGO implements the main hnsw API，Brute force index is not implemented as it is rarely used.

For more information, please consult documents of the hnswlib projects.

References

Malkov, Yu A., and D. A. Yashunin. "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs." TPAMI, preprint: [https://arxiv.org/abs/1603.09320]