Day 1 announcements: o1 is fully here
Saturday, December 07, 2024
12 Days of OpenAI: o1 pro
AI: fast embeddings search with SIMD (JS, Python, ...)
usearch - npm
Smaller & Faster Single-File
Similarity Search & Clustering Engine for Vectors
C++ 11 • Python 3 • JavaScript • Java • Rust • C 99 • Objective-C • Swift • C# • GoLang • Wolfram
Linux • MacOS • Windows • iOS • Android • WebAssembly • SQLite3
✅ 10x faster HNSW implementation than FAISS.
✅ Simple and extensible single C++11 header library.
✅ Trusted by giants like Google and DBs like ClickHouse & DuckDB.
✅ SIMD-optimized and user-defined metrics with JIT compilation.
✅ Hardware-agnostic f16 & i8 - half-precision & quarter-precision support.
unum-cloud/usearch: Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍 @GitHub
Unum · USearch 2.16.2 documentation @GitHub
Smaller & Faster Single-File
Similarity Search & Clustering Engine for Vectors
C++ 11 • Python 3 • JavaScript • Java • Rust • C 99 • Objective-C • Swift • C# • GoLang • Wolfram
Linux • MacOS • Windows • iOS • Android • WebAssembly • SQLite3
✅ 10x faster HNSW implementation than FAISS.
✅ Simple and extensible single C++11 header library.
✅ Trusted by giants like Google and DBs like ClickHouse & DuckDB.
✅ SIMD-optimized and user-defined metrics with JIT compilation.
✅ Hardware-agnostic f16 & i8 - half-precision & quarter-precision support.
unum-cloud/usearch: Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍 @GitHub
Unum · USearch 2.16.2 documentation @GitHub
USearch is a high-performance library for building and querying vector search indexes, optimized for Node.js and WASM environments.
Alternative
- Zero-dependency header-only C 99 library with bindings for Python and JavaScript.
- Targets ARM NEON, SVE, x86 AVX2, AVX-512 (VNNI, FP16) hardware backends.
- Zero-copy compatible with NumPy, PyTorch, TensorFlow, and other tensors.
- Handles f64 double-, f32 single-, and f16 half-precision, i8 integral, and binary vectors.
- Up to 200x faster than scipy.spatial.distance and numpy.inner.
- Used in USearch and several DBMS products.
JavaScript
npm i @sroussey/simsimd
import { dot } from '@sroussey/simsimd';
const vector1 = Float32Array.from([1, 2, 3]);
const vector2 = Float32Array.from([4, 5, 6]);
const dotProduct = dot(vector1, vector2);
// Calculate cosine similarity using the dot product
const cosineSimilarity = dotProduct / (magnitude(vector1) * magnitude(vector2));
Python
pip install simsimd
import simsimd import numpy as np vec1 = np.random.randn(1536).astype(np.float32) vec2 = np.random.randn(1536).astype(np.float32) dist = simsimd.cosine(vec1, vec2)
Subscribe to:
Posts (Atom)