From 406731d84ebfded6ba4f9b11c81c9b2a270495e0 Mon Sep 17 00:00:00 2001
From: Jianshu_Zhao <38149286+jianshu93@users.noreply.github.com>
Date: Mon, 8 Aug 2022 22:34:34 -0400
Subject: [PATCH] Add rust implementation

A beautiful Rust implementation. I have run benchmarks for various dataset with very good performance and recall. More metric distance are supported including hamming, Hellinger distance, Jensen-Shannon distance between probability distributions (f32 and f64).  There is  A Trait to enable the user to implement its own distances. It takes as data slices of types T satisfying T:Serialize+Clone+Send+Sync.
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 9bcb6775..5ec6ebed 100644
--- a/README.md
+++ b/README.md
@@ -267,7 +267,7 @@ https://github.com/dbaranchuk/ivf-hnsw
 * Java bindings using Java Native Access: https://github.com/stepstone-tech/hnswlib-jna
 * .Net implementation: https://github.com/microsoft/HNSW.Net
 * CUDA implementation: https://github.com/js1010/cuhnsw
-
+* Rust implementation for memory and thread safety purposes and There is  A Trait to enable the user to implement its own distances. It takes as data slices of types T satisfying T:Serialize+Clone+Send+Sync.: https://github.com/jean-pierreBoth/hnswlib-rs
 
 ### 200M SIFT test reproduction 
 To download and extract the bigann dataset (from root directory):