Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

Latest commit

 

History

History
20 lines (9 loc) · 1020 Bytes

similarity-search-in-eigendb.md

File metadata and controls

20 lines (9 loc) · 1020 Bytes
description
How it's done!

Similarity Search in EigenDB

Similarity search algorithm

EigenDB employs the Hierarchical Navigable Small World (HNSW) algorithm to perform similarity search with the highest level of efficiency and speed.

Implementation

The HNSW algorithm is implemented in EigenDB through our open-source Go library hnswgo. The library is a Go wrapper for hnswlib, the C++ implementation of the HNSW algorithm.

This library allows EigenDB to perform database operations solely using Go while never having to write any C/C++ code. In addition, the wrapper was made into an open-source library instead of including it in EigenDB, as this allows other developers to easily utilize the HNSW algorithm purely with Go. This means developers won't have to write their own wrappers, mess around in C/C++, or even implement the HNSW algorithm from scratch in Go.