Portable mixed-precision BLAS-like vector math library for x86 and ARM
Hot-loop cosine similarity for f32 slices. Auto-vectorized scalar core, optional precompute-norms helper. Zero deps.
High-performance vector database engine written in Rust
In-memory vector search and similarity operations for OxiFY (ported from OxiRS)
SIMD-accelerated MaxSim, cosine, diversity (MMR/DPP) for vector search and RAG pipelines
SIMD-accelerated vector similarity primitives with binary, ternary, and scalar quantization
CLI for testing and benchmarking ruvector-router-core
Locality Sensitive Hashing for Angular Similarity
Batched cosine, dot, L2 distance for f32 embeddings, with a heap-based top-k selector. No BLAS, no allocator surprises.
Lightweight ndarray-native compute and rerank layer for embedding vectors
Cosine Locality-Sensitive Hashing
OSpipe: RuVector-enhanced personal AI memory system integrating with Screenpipe
This gem provides a method for calculating the cosine similarity between two vector embeddings.
Document similarity calculations using cosine similarity and TF-IDF weights
Calculate cosine similarity between given 2 sentence strings
This plugin calculates and adds related posts to your Bridgetown site using TF-IDF and cosine similarity.
== Description This gem provides some methods for calculating similarities of two strings. === Currently implemented - Cosine similarity - Levenshtein distance/similarity === Planned - Hamming similarity
Anngler is an approximate nearest neighbor search for points in n-dimensional space that are close in terms of cosine distance to a given point. The gem is built with serverless architecture in mind with Redis but it also offers a local in-memory storage.
DEPRECATED PROJECT. MIGRATED TO PYTHON: https://github.com/seoanezonjic/NetAnalyzer. NetAnalyzer is a useful network analysis tool developed in Ruby that can 1) analyse any type of unweighted network, regardless of the number of layers, 2) calculate the relationship between different layers, using various association indices (Jaccard, Simpson, PCC, geometric, cosine and hypergeometric) and 3) validate the results
Provides RobotLab::DocumentStore — a thread-safe, in-memory semantic search store backed by fastembed (BAAI/bge-small-en-v1.5). Store text documents by key and retrieve the closest matches to a natural-language query using cosine similarity. Works standalone or as a drop-in extension for robot_lab agents and networks.
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.