Fast approximate nearest neighbor searching in Rust, based on HNSW index
Go to file
Kuba Jaroszewski 9d8c83fc38 Add Cosine distance metric 2023-02-16 21:55:50 +01:00
.cargo Fix rustflags setup for PyO3 2021-11-10 09:27:19 +01:00
.github py: looks like we need --no-sdist for publish after all 2023-02-02 13:12:25 +01:00
.vscode First cut of python bindings update 2021-05-21 17:34:33 +02:00
distance-metrics Add Cosine distance metric 2023-02-16 21:55:50 +01:00
instant-distance Remove authors from Cargo metadata (per RFC 3052) 2023-01-27 11:09:41 +01:00
instant-distance-py Add Cosine distance metric 2023-02-16 21:55:50 +01:00
.gitignore Ignore .DS_Store cruft 2021-05-17 13:37:11 +02:00
Cargo.toml Replace Euclid metric implementation 2023-02-16 21:50:13 +01:00
LICENSE Add LICENSE 2021-08-18 22:05:57 +02:00
Makefile Add Cosine distance metric 2023-02-16 21:55:50 +01:00
README.md Link to translation article 2021-09-06 16:55:02 +02:00
cover.svg Add files via upload 2021-04-20 11:07:03 -07:00
deny.toml Add configuration for cargo-deny 2020-12-16 10:17:29 +01:00

README.md

Cover logo

Instant Distance: fast HNSW indexing

Build status License: MIT License: Apache 2.0

Instance Distance is a fast pure-Rust implementation of the Hierarchical Navigable Small Worlds paper by Malkov and Yashunin for finding approximate nearest neighbors. This implementation powers the InstantDomainSearch.com backend services used for word vector indexing.

What it does

Instant Distance is an implementation of a fast approximate nearest neighbor search algorithm. The algorithm is used to find the closest point(s) to a given point in a set. As one example, it can be used to make simple translations.

Using the library

Rust

[dependencies]
instant-distance = "0.5.0"

Example

use instant_distance::{Builder, Search};

fn main() {
    let points = vec![Point(255, 0, 0), Point(255, 0, 0), Point(255, 0, 0)];
    let values = vec!["red", "green", "blue"];

    let map = Builder::default().build(points, values);
    let mut search = Search::default();

    let cambridge_blue = Point(163, 193, 173);

    let closest_point = map.search(&cambridge_blue, &mut search).next().unwrap();

    println!("{:?}", closest_point.value);
}

#[derive(Clone, Copy, Debug)]
struct Point(isize, isize, isize);

impl instant_distance::Point for Point {
    fn distance(&self, other: &Self) -> f32 {
        // Euclidean distance metric
        (((self.0 - other.0).pow(2) + (self.1 - other.1).pow(2) + (self.2 - other.2).pow(2)) as f32)
            .sqrt()
    }
}

Testing

Rust:

cargo t -p instant-distance --all-features

Python:

make test-python