usearch 0.1.1

The Mighty Tiny Vector Search Engine with Automatic Quantization and Hardware Acceleration

USearch

C++11 Single Header Vector Search
Compact, yet Powerful

               

• Single C++11 header implementation, easily extendible.
• 4B+ sized space efficient point-clouds with uint40_t.
• Half-precision support with maratyszcza/fp16.
• View from disk, without loading into RAM.
• Any metric, includes:
  • Euclidean, Dot-product, Cosine,
  • Jaccard, Hamming, Haversine.
  • Hardware-accelerated ashvardanian/simsimd.
• Variable dimensionality vectors.
• Don't copy vectors if not needed.
• Bring your threads.
• Multiple vectors per label.
• CPython bindings for Python 3: pip install usearch
• Node.js bindings for JavaScript: npm install usearch
• Rust language bindings.
• Wolfram language bindings.
• For Linux: GCC, Clang.
• For MacOS: Apple Clang.
• For Windows.
• Multi-index lookups in Python.
• Thread-safe reserve.
• Distributed construction.

Usage

C++

To use in a C++ project simply copy the include/usearch/usearch.hpp header into your project.

using namespace unum::usearch;

index_gt<cos_gt<float>> index;
float vec[3] = {0.1, 0.3, 0.2};
index.add(/* label: */ 42, /* vector: */ {&vec, 3});
index.search(
  /* query: */ {&vec, 3}, 10 /* results */,
  /* callback: */ [](std::size_t label, float distance) { });

Alternatively fetch it with CMake:

FetchContent_Declare(usearch GIT_REPOSITORY https://github.com/unum-cloud/usearch.git)
FetchContent_MakeAvailable(usearch)

Features

Bring your Threads

Performance

TODO

• JavaScript: Allow calling from "worker threads".
• Rust: Allow passing a custom thread ID.