Fast approximate nearest neighbor searching in Rust, based on HNSW index
Go to file
Dirkjan Ochtman c9f62ad3fb py: use integers as point identifiers 2021-03-18 21:02:14 +01:00
.cargo Initial version of Python bindings 2021-03-18 12:59:39 +01:00
.github/workflows Skip Python bindings in CI for now 2021-03-18 12:59:39 +01:00
instant-distance Add Search::get() helper for bindings 2021-03-18 12:59:39 +01:00
instant-distance-py py: use integers as point identifiers 2021-03-18 21:02:14 +01:00
.gitignore Ignore Python build artifacts 2021-03-18 12:59:39 +01:00
Cargo.toml Initial version of Python bindings 2021-03-18 12:59:39 +01:00
Makefile Add Makefile to help with testing 2021-03-18 12:59:39 +01:00
README.md Add an inital README 2020-12-16 10:30:45 +01:00
cover.svg Add an inital README 2020-12-16 10:30:45 +01:00
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 will power the InstantDomainSearch.com backend services used for word vector indexing.