BETAmodules.com is in beta — open to partnerships & joint ventures.Build with us
modules.com
⌘K

hanny

v0.2.2RubyGems· Ruby

Hanny is a Hash-based Approximate Nearest Neighbor (ANN) search library in Ruby. Hash-based ANN converts vector data into binary codes and builds a hash table by using the binary codes as hash keys. To build the hash table, Hanny uses Locality Sensitive Hashing (LSH) of approximating cosine similarity. It is known that if the code length is sufficiently long (ex. greater than 128-bit), LSH can obtain high search performance. In the experiment, Hanny achieved about twenty times faster search speed than the brute-force search by Euclidean distance.

The verdict
Abandoned. Last published 3 years ago. No recent activity — look for a maintained alternative.
No recent activity — look for a maintained alternative.
Live from the RubyGems registry · derived rules, not AI
How it scores
MaintenanceAbandoned
PopularityNiche
SecurityClean
LicensePermissive
DepsZero deps
Maintenance
Last published 3 years ago.
Popularity
8 downloads / week
Security
No known advisories for this version (OSV).
License
BSD-2-Clause
Dependencies
No runtime dependencies
Recent releases
  • 0.2.23 years ago
  • 0.2.14 years ago
  • 0.2.04 years ago
  • 0.1.08 years ago
hanny — Hanny is a Hash-based Approximate Nearest Neighbor (ANN) search library in Ruby. Hash-based ANN converts vector data into binary codes and builds a hash table by using the binary codes as hash keys. To build the hash table, Hanny uses Locality Sensitive Hashing (LSH) of approximating cosine similarity. It is known that if the code length is sufficiently long (ex. greater than 128-bit), LSH can obtain high search performance. In the experiment, Hanny achieved about twenty times faster search speed than the brute-force search by Euclidean distance. (Ruby / RubyGems) · Modules