usearch 2.8.3 → 2.8.4

package/csharp/DEV_SETUP.md

@@ -11,7 +11,7 @@ To obtain all libraries, download the artifacts generated by the GitHub workflow
 
 To get a library for your current platform (Linux or Macos), execute: `./eng/build_lib.sh`.
 
-For more details, refer to the [compilation guide](https://github.com/unum-cloud/usearch/blob/main/docs/compilation.md).
+For more details, refer to the [compilation guide](https://github.com/unum-cloud/usearch/blob/main/CONTRIBUTING.md).
 
 # Build and Test
 

package/csharp/nuget/nuget-package.props

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="utf-8"?>
 <Project>
   <PropertyGroup>
-    <Version Condition="'$(Version)' == ''">2.8.3</Version>
+    <Version Condition="'$(Version)' == ''">2.8.4</Version>
 
     <Authors>Unum</Authors>
     <Company>Unum</Company>

package/docs/{compilation.rst → contributing.rst}

@@ -1,5 +1,5 @@
 ========================
-Compilation
+Contributing
 ========================
 
-.. mdinclude:: compilation.md
+.. mdinclude:: ../CONTRIBUTING.md

package/docs/index.rst

@@ -22,7 +22,7 @@ Overview
    :hidden:
    :caption: �
 
-   compilation
+   contributing
    benchmarks
    format
 

package/include/usearch/index.hpp

@@ -11,7 +11,7 @@
 
 #define USEARCH_VERSION_MAJOR 2
 #define USEARCH_VERSION_MINOR 8
-#define USEARCH_VERSION_PATCH 3
+#define USEARCH_VERSION_PATCH 4
 
 // Inferring C++ version
 // https://stackoverflow.com/a/61552074

package/include/usearch/index_dense.hpp

@@ -323,7 +323,7 @@ class index_dense_gt {
     /// @brief Schema: input buffer, bytes in input buffer, output buffer.
     using cast_t = std::function<bool(byte_t const*, std::size_t, byte_t*)>;
     /// @brief Punned index.
-    using index_t = index_gt<                 //
+    using index_t = index_gt<                        //
         distance_t, vector_key_t, compressed_slot_t, //
         dynamic_allocator_t, tape_allocator_t>;
     using index_allocator_t = aligned_allocator_gt<index_t, 64>;
@@ -1512,10 +1512,14 @@ class index_dense_gt {
      *  @brief  Implements clustering, classifying the given objects (vectors of member keys)
      *          into a given number of clusters.
      *
-     *  @param[in] queries_begin Iterator targeting the fiest query.
-     *  @param[in] queries_end
+     *  @param[in] queries_begin Iterator pointing to the first query.
+     *  @param[in] queries_end Iterator pointing to the last query.
      *  @param[in] executor Thread-pool to execute the job in parallel.
      *  @param[in] progress Callback to report the execution progress.
+     *  @param[in] config Configuration parameters for clustering.
+     *
+     *  @param[out] cluster_keys Pointer to the array where the cluster keys will be exported.
+     *  @param[out] cluster_distances Pointer to the array where the distances to those centroids will be exported.
      */
     template <                                   //
         typename queries_iterator_at,            //
@@ -1526,7 +1530,7 @@ class index_dense_gt {
         queries_iterator_at queries_begin,      //
         queries_iterator_at queries_end,        //
         index_dense_clustering_config_t config, //
-        vector_key_t* cluster_keys,                    //
+        vector_key_t* cluster_keys,             //
         distance_t* cluster_distances,          //
         executor_at&& executor = executor_at{}, //
         progress_at&& progress = progress_at{}) {
@@ -1715,7 +1719,7 @@ class index_dense_gt {
     }
 
     template <typename scalar_at>
-    add_result_t add_(                      //
+    add_result_t add_(                             //
         vector_key_t key, scalar_at const* vector, //
         std::size_t thread, bool force_vector_copy, cast_t const& cast) {
 
@@ -1811,8 +1815,8 @@ class index_dense_gt {
     }
 
     template <typename scalar_at>
-    aggregated_distances_t distance_between_( //
-        vector_key_t key, scalar_at const* vector,   //
+    aggregated_distances_t distance_between_(      //
+        vector_key_t key, scalar_at const* vector, //
         std::size_t thread, cast_t const& cast) const {
 
         // Cast the vector, if needed for compatibility with `metric_`

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "usearch",
-    "version": "2.8.3",
+    "version": "2.8.4",
     "description": "Smaller & Faster Single-File Vector Search Engine from Unum",
     "author": "Ash Vardanian (https://ashvardanian.com/)",
     "license": "Apache 2.0",

package/python/README.md

@@ -10,7 +10,7 @@ pip install usearch
 
 ```python
 import numpy as np
-from usearch.index import Index
+from usearch.index import Index, Matches
 
 index = Index(
     ndim=3, # Define the number of dimensions in input vectors

package/simsimd/CMakeLists.txt

@@ -48,7 +48,7 @@ if(CMAKE_CXX_COMPILER_ID MATCHES "^(Apple)?Clang$")
   endif()
   add_compile_options(-pedantic -ferror-limit=1)
 elseif(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-  add_compile_options(-march=native -pedantic -fmax-errors=1)
+  add_compile_options(-march=native -pedantic -fmax-errors=1 -Wno-tautological-constant-compare)
 elseif(CMAKE_CXX_COMPILER_ID STREQUAL "IntelLLVM")
   add_compile_options(-w -ferror-limit=1)
 endif()

package/simsimd/README.md

@@ -1,5 +1,11 @@
 # SimSIMD 📏
 
+<div>
+<a href="https://pypi.org/project/simsimd/"> <img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/simsimd?label=pypi%20downloads"> </a>
+<a href="https://www.npmjs.com/package/simsimd"> <img alt="npm" src="https://img.shields.io/npm/dy/simsimd?label=npm%20dowloads"> </a>
+<img alt="GitHub code size in bytes" src="https://img.shields.io/github/languages/code-size/ashvardanian/simsimd">
+</div>
+
 ## Efficient Alternative to [`scipy.spatial.distance`][scipy] and [`numpy.inner`][numpy]
 
 SimSIMD leverages SIMD intrinsics, capabilities that only select compilers effectively utilize. This framework supports conventional AVX2 instructions on x86, NEON on Arm, as well as __rare__ AVX-512 FP16 instructions on x86 and Scalable Vector Extensions (SVE) on Arm. Designed specifically for Machine Learning contexts, it's optimized for handling high-dimensional vector embeddings.
@@ -189,7 +195,7 @@ __To test and benchmark JavaScript bindings__:
 ```sh
 npm install --dev
 npm test
-npm bench
+npm run bench
 ```
 
 __To test and benchmark GoLang bindings__:

package/simsimd/include/simsimd/probability.h

@@ -52,17 +52,17 @@
 extern "C" {
 #endif
 
-SIMSIMD_MAKE_KL(serial, f32, f32, SIMSIMD_IDENTIFY, 1e-6) // simsimd_serial_f32_kl
-SIMSIMD_MAKE_JS(serial, f32, f32, SIMSIMD_IDENTIFY, 1e-6) // simsimd_serial_f32_js
+SIMSIMD_MAKE_KL(serial, f32, f32, SIMSIMD_IDENTIFY, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_serial_f32_kl
+SIMSIMD_MAKE_JS(serial, f32, f32, SIMSIMD_IDENTIFY, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_serial_f32_js
 
-SIMSIMD_MAKE_KL(serial, f16, f32, SIMSIMD_UNCOMPRESS_F16, 1e-3) // simsimd_serial_f16_kl
-SIMSIMD_MAKE_JS(serial, f16, f32, SIMSIMD_UNCOMPRESS_F16, 1e-3) // simsimd_serial_f16_js
+SIMSIMD_MAKE_KL(serial, f16, f32, SIMSIMD_UNCOMPRESS_F16, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_serial_f16_kl
+SIMSIMD_MAKE_JS(serial, f16, f32, SIMSIMD_UNCOMPRESS_F16, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_serial_f16_js
 
-SIMSIMD_MAKE_KL(accurate, f32, f64, SIMSIMD_IDENTIFY, 1e-6) // simsimd_accurate_f32_kl
-SIMSIMD_MAKE_JS(accurate, f32, f64, SIMSIMD_IDENTIFY, 1e-6) // simsimd_accurate_f32_js
+SIMSIMD_MAKE_KL(accurate, f32, f64, SIMSIMD_IDENTIFY, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_accurate_f32_kl
+SIMSIMD_MAKE_JS(accurate, f32, f64, SIMSIMD_IDENTIFY, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_accurate_f32_js
 
-SIMSIMD_MAKE_KL(accurate, f16, f64, SIMSIMD_UNCOMPRESS_F16, 1e-6) // simsimd_accurate_f16_kl
-SIMSIMD_MAKE_JS(accurate, f16, f64, SIMSIMD_UNCOMPRESS_F16, 1e-6) // simsimd_accurate_f16_js
+SIMSIMD_MAKE_KL(accurate, f16, f64, SIMSIMD_UNCOMPRESS_F16, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_accurate_f16_kl
+SIMSIMD_MAKE_JS(accurate, f16, f64, SIMSIMD_UNCOMPRESS_F16, SIMSIMD_F32_DIVISION_EPSILON) // simsimd_accurate_f16_js
 
 #if SIMSIMD_TARGET_ARM
 #if SIMSIMD_TARGET_ARM_NEON
@@ -108,7 +108,7 @@ __attribute__((target("+simd"))) //
 inline static simsimd_f32_t
 simsimd_neon_f32_kl(simsimd_f32_t const* a, simsimd_f32_t const* b, simsimd_size_t n) {
     float32x4_t sum_vec = vdupq_n_f32(0);
-    simsimd_f32_t epsilon = 1e-6;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     float32x4_t epsilon_vec = vdupq_n_f32(epsilon);
     simsimd_size_t i = 0;
     for (; i + 4 <= n; i += 4) {
@@ -129,7 +129,7 @@ simsimd_neon_f32_kl(simsimd_f32_t const* a, simsimd_f32_t const* b, simsimd_size
 __attribute__((target("+simd"))) inline static simsimd_f32_t
 simsimd_neon_f32_js(simsimd_f32_t const* a, simsimd_f32_t const* b, simsimd_size_t n) {
     float32x4_t sum_vec = vdupq_n_f32(0);
-    simsimd_f32_t epsilon = 1e-6;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     float32x4_t epsilon_vec = vdupq_n_f32(epsilon);
     simsimd_size_t i = 0;
     for (; i + 4 <= n; i += 4) {
@@ -147,11 +147,11 @@ simsimd_neon_f32_js(simsimd_f32_t const* a, simsimd_f32_t const* b, simsimd_size
     simsimd_f32_t log2_normalizer = 0.693147181f;
     simsimd_f32_t sum = vaddvq_f32(sum_vec) * log2_normalizer;
     for (; i < n; ++i) {
-        simsimd_f32_t mi = a[i] + b[i];
+        simsimd_f32_t mi = 0.5f * (a[i] + b[i]);
         sum += a[i] * SIMSIMD_LOG((a[i] + epsilon) / (mi + epsilon));
         sum += b[i] * SIMSIMD_LOG((b[i] + epsilon) / (mi + epsilon));
     }
-    return sum * 0.5f;
+    return sum;
 }
 
 /*
@@ -168,7 +168,7 @@ __attribute__((target("+simd+fp16"))) //
 inline static simsimd_f32_t
 simsimd_neon_f16_kl(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size_t n) {
     float32x4_t sum_vec = vdupq_n_f32(0);
-    simsimd_f32_t epsilon = 1e-3;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     float32x4_t epsilon_vec = vdupq_n_f32(epsilon);
     simsimd_size_t i = 0;
     for (; i + 4 <= n; i += 4) {
@@ -191,7 +191,7 @@ __attribute__((target("+simd+fp16"))) //
 inline static simsimd_f32_t
 simsimd_neon_f16_js(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size_t n) {
     float32x4_t sum_vec = vdupq_n_f32(0);
-    simsimd_f32_t epsilon = 1e-3;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     float32x4_t epsilon_vec = vdupq_n_f32(epsilon);
     simsimd_size_t i = 0;
     for (; i + 4 <= n; i += 4) {
@@ -211,11 +211,11 @@ simsimd_neon_f16_js(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size
     for (; i < n; ++i) {
         simsimd_f32_t ai = SIMSIMD_UNCOMPRESS_F16(a[i]);
         simsimd_f32_t bi = SIMSIMD_UNCOMPRESS_F16(b[i]);
-        simsimd_f32_t mi = ai + bi;
+        simsimd_f32_t mi = 0.5f * (ai + bi);
         sum += ai * SIMSIMD_LOG((ai + epsilon) / (mi + epsilon));
         sum += bi * SIMSIMD_LOG((bi + epsilon) / (mi + epsilon));
     }
-    return sum / 2;
+    return sum;
 }
 
 #endif // SIMSIMD_TARGET_ARM_NEON
@@ -268,7 +268,7 @@ __attribute__((target("avx2,f16c,fma"))) //
 inline static simsimd_f32_t
 simsimd_avx2_f16_kl(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size_t n) {
     __m256 sum_vec = _mm256_set1_ps(0);
-    simsimd_f32_t epsilon = 1e-5;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     __m256 epsilon_vec = _mm256_set1_ps(epsilon);
     simsimd_size_t i = 0;
     for (; i + 8 <= n; i += 8) {
@@ -300,7 +300,7 @@ __attribute__((target("avx2,f16c,fma"))) //
 inline static simsimd_f32_t
 simsimd_avx2_f16_js(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size_t n) {
     __m256 sum_vec = _mm256_set1_ps(0);
-    simsimd_f32_t epsilon = 1e-5;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     __m256 epsilon_vec = _mm256_set1_ps(epsilon);
     simsimd_size_t i = 0;
     for (; i + 8 <= n; i += 8) {
@@ -374,7 +374,7 @@ __attribute__((target("avx512f,avx512vl,bmi2"))) //
 inline static simsimd_f32_t
 simsimd_avx512_f32_kl(simsimd_f32_t const* a, simsimd_f32_t const* b, simsimd_size_t n) {
     __m512 sum_vec = _mm512_set1_ps(0);
-    simsimd_f32_t epsilon = 1e-6;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     __m512 epsilon_vec = _mm512_set1_ps(epsilon);
     __m512 a_vec, b_vec;
 
@@ -405,7 +405,7 @@ inline static simsimd_f32_t
 simsimd_avx512_f32_js(simsimd_f32_t const* a, simsimd_f32_t const* b, simsimd_size_t n) {
     __m512 sum_a_vec = _mm512_set1_ps(0);
     __m512 sum_b_vec = _mm512_set1_ps(0);
-    simsimd_f32_t epsilon = 1e-6;
+    simsimd_f32_t epsilon = SIMSIMD_F32_DIVISION_EPSILON;
     __m512 epsilon_vec = _mm512_set1_ps(epsilon);
     __m512 a_vec, b_vec;
 
@@ -425,8 +425,8 @@ simsimd_avx512_f32_js_cycle:
     __mmask16 nonzero_mask_b = _mm512_cmp_ps_mask(b_vec, epsilon_vec, _CMP_GE_OQ);
     __mmask16 nonzero_mask = nonzero_mask_a & nonzero_mask_b;
     __m512 m_recip_approx = _mm512_rcp14_ps(m_vec);
-    __m512 ratio_a_vec = _mm512_mul_ps(a_vec, m_recip_approx);
-    __m512 ratio_b_vec = _mm512_mul_ps(b_vec, m_recip_approx);
+    __m512 ratio_a_vec = _mm512_div_ps(a_vec, m_vec);
+    __m512 ratio_b_vec = _mm512_div_ps(b_vec, m_vec);
     __m512 log_ratio_a_vec = simsimd_avx512_f32_log2(ratio_a_vec);
     __m512 log_ratio_b_vec = simsimd_avx512_f32_log2(ratio_b_vec);
     sum_a_vec = _mm512_maskz_fmadd_ps(nonzero_mask, a_vec, log_ratio_a_vec, sum_a_vec);
@@ -472,7 +472,7 @@ __attribute__((target("avx512f,avx512vl,avx512fp16,bmi2"))) //
 inline static simsimd_f32_t
 simsimd_avx512_f16_kl(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size_t n) {
     __m512h sum_vec = _mm512_set1_ph((_Float16)0);
-    __m512h epsilon_vec = _mm512_set1_ph((_Float16)1e-6f);
+    __m512h epsilon_vec = _mm512_set1_ph((_Float16)SIMSIMD_F16_DIVISION_EPSILON);
     __m512h a_vec, b_vec;
 
 simsimd_avx512_f16_kl_cycle:
@@ -502,7 +502,7 @@ inline static simsimd_f32_t
 simsimd_avx512_f16_js(simsimd_f16_t const* a, simsimd_f16_t const* b, simsimd_size_t n) {
     __m512h sum_a_vec = _mm512_set1_ph((_Float16)0);
     __m512h sum_b_vec = _mm512_set1_ph((_Float16)0);
-    __m512h epsilon_vec = _mm512_set1_ph((_Float16)1e-6f);
+    __m512h epsilon_vec = _mm512_set1_ph((_Float16)SIMSIMD_F16_DIVISION_EPSILON);
     __m512h a_vec, b_vec;
 
 simsimd_avx512_f16_js_cycle:

package/simsimd/include/simsimd/types.h

@@ -91,6 +91,14 @@
 #define SIMSIMD_LOG(x) (logf(x))
 #endif
 
+#ifndef SIMSIMD_F32_DIVISION_EPSILON
+#define SIMSIMD_F32_DIVISION_EPSILON 1e-7
+#endif
+
+#ifndef SIMSIMD_F16_DIVISION_EPSILON
+#define SIMSIMD_F16_DIVISION_EPSILON 1e-3
+#endif
+
 #ifdef __cplusplus
 extern "C" {
 #endif

package/simsimd/javascript/{test.js → test/simsimd.test.js}

@@ -4,12 +4,6 @@ import assert from 'node:assert';
 
 const simsimd = bindings('simsimd');
 
-const f32Array1 = new Float32Array([1.0, 2.0, 3.0]);
-const f32Array2 = new Float32Array([4.0, 5.0, 6.0]);
-
-const u8Array1 = new Uint8Array([1, 2, 3]);
-const u8Array2 = new Uint8Array([4, 5, 6]);
-
 function assertAlmostEqual(actual, expected, tolerance = 1e-6) {
     const lowerBound = expected - tolerance;
     const upperBound = expected + tolerance;
@@ -17,20 +11,26 @@ function assertAlmostEqual(actual, expected, tolerance = 1e-6) {
 }
 
 test('Distance from itself', () => {
-    assertAlmostEqual(simsimd.sqeuclidean(f32Array1, f32Array1), 0.0, 0.01);
-    assertAlmostEqual(simsimd.cosine(f32Array1, f32Array1), 0.0, 0.01);
 
-    // Inner-product distance on non-nroamalized vectors would yield:
-    // 1 - 1 - 4 - 9 = -13
-    assertAlmostEqual(simsimd.inner(f32Array1, f32Array1), -13.0, 0.01);
+    const f32s = new Float32Array([1.0, 2.0, 3.0]);
+    assertAlmostEqual(simsimd.sqeuclidean(f32s, f32s), 0.0, 0.01);
+    assertAlmostEqual(simsimd.cosine(f32s, f32s), 0.0, 0.01);
 
-    assertAlmostEqual(simsimd.kullbackleibler(f32Array1, f32Array1), 0.0, 0.01);
-    assertAlmostEqual(simsimd.jensenshannon(f32Array1, f32Array1), 0.0, 0.01);
+    const f32sNormalized = new Float32Array([1.0 / Math.sqrt(14), 2.0 / Math.sqrt(14), 3.0 / Math.sqrt(14)]);
+    assertAlmostEqual(simsimd.inner(f32sNormalized, f32sNormalized), 0.0, 0.01);
 
-    assertAlmostEqual(simsimd.hamming(u8Array1, u8Array1), 0.0, 0.01);
-    assertAlmostEqual(simsimd.jaccard(u8Array1, u8Array1), 0.0, 0.01);
+    const f32sDistribution = new Float32Array([1.0 / 6, 2.0 / 6, 3.0 / 6]);
+    assertAlmostEqual(simsimd.kullbackleibler(f32sDistribution, f32sDistribution), 0.0, 0.01);
+    assertAlmostEqual(simsimd.jensenshannon(f32sDistribution, f32sDistribution), 0.0, 0.01);
+
+    const u8s = new Uint8Array([1, 2, 3]);
+    assertAlmostEqual(simsimd.hamming(u8s, u8s), 0.0, 0.01);
+    assertAlmostEqual(simsimd.jaccard(u8s, u8s), 0.0, 0.01);
 });
 
+const f32Array1 = new Float32Array([1.0, 2.0, 3.0]);
+const f32Array2 = new Float32Array([4.0, 5.0, 6.0]);
+
 test('Squared Euclidean Distance', () => {
     const result = simsimd.sqeuclidean(f32Array1, f32Array2);
     assertAlmostEqual(result, 27.0, 0.01);

package/simsimd/package.json

@@ -1,14 +1,14 @@
 {
   "name": "simsimd",
-  "version": "3.3.0",
+  "version": "3.5.3",
   "description": "Vector Similarity Functions 3x-200x Faster than SciPy and NumPy",
   "author": "Ash Vardanian",
   "license": "Apache 2.0",
   "main": "javascript/simsimd.js",
   "type": "module",
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/ashvardanian/simsimd.git"
+  "scripts": {
+    "test": "node --test ./javascript/test",
+    "bench": "node ./javascript/bench.js"
   },
   "gypfile": true,
   "engines": {
@@ -19,10 +19,6 @@
     "bindings": "~1.2.1",
     "node-addon-api": "^3.0.0"
   },
-  "scripts": {
-    "test": "node --test ./javascript/test.js",
-    "bench": "node ./javascript/bench.js"
-  },
   "devDependencies": {
     "benchmark": "^2.1.4",
     "mathjs": "^11.11.2",

package/simsimd/setup.py

@@ -27,6 +27,9 @@ if sys.platform == "linux":
     compile_args.append("-fopenmp")
     link_args.append("-lgomp")
 
+    # Add vectorized `logf` implementation from the `glibc`
+    link_args.append("-lm")
+
 if sys.platform == "darwin":
     compile_args.append("-std=c11")
     compile_args.append("-O3")

package/wasmer.toml

@@ -1,6 +1,6 @@
 [package]
 name="unum/usearch"
-version="2.8.3"
+version="2.8.4"
 description="Smaller & Faster Single-File Vector Search Engine from Unum"
 license="Apache-2.0"
 readme="README.md"

package/docs/compilation.md

@@ -1,215 +0,0 @@
-# Compiling USearch
-
-This document describes the workflow for advanced USearch users and enthusiasts willing to contribute to the project.
-Before building the first time, please pull submodules.
-
-```sh
-git submodule update --init --recursive
-```
-
-## C++11
-
-Linux:
-
-```sh
-sudo apt-get update
-sudo apt-get install cmake build-essential libjemalloc-dev
-cmake -B ./build_release \
-    -DCMAKE_BUILD_TYPE=Release \
-    -DUSEARCH_USE_OPENMP=1 \
-    -DUSEARCH_USE_SIMSIMD=1 \
-    -DUSEARCH_USE_JEMALLOC=1 \
-    -DUSEARCH_BUILD_TEST_CPP=1 \
-    -DUSEARCH_BUILD_BENCH_CPP=1 \
-    -DUSEARCH_BUILD_LIB_C=1 \
-    -DUSEARCH_BUILD_TEST_C=1 \
-    -DUSEARCH_USE_NATIVE_F16=1 \
-    && \
-    make -C ./build_release -j
-```
-
-MacOS:
-
-```sh
-brew install libomp llvm
-cmake -B ./build_release \
-    -DCMAKE_C_COMPILER="/opt/homebrew/opt/llvm/bin/clang" \
-    -DCMAKE_CXX_COMPILER="/opt/homebrew/opt/llvm/bin/clang++" \
-    -DUSEARCH_USE_OPENMP=1 \
-    -DUSEARCH_USE_SIMSIMD=1 \
-    -DUSEARCH_BUILD_BENCH_CPP=1 \
-    -DUSEARCH_BUILD_TEST_CPP=1 \
-    && \
-    make -C ./build_release -j
-```
-
-Linting:
-
-```sh
-cppcheck --enable=all --force --suppress=cstyleCast --suppress=unusedFunction \
-    include/usearch/index.hpp \
-    include/index_dense.hpp \
-    include/index_plugins.hpp
-```
-
-Testing:
-
-```sh
-cmake -DUSEARCH_BUILD_TEST_CPP=1 -B ./build_debug
-cmake --build ./build_debug --config Debug
-./build_debug/test_cpp
-```
-
-## Python 3
-
-Use PyTest to validate the build.
-The `-s` option will disable capturing the logs.
-The `-x` option will exit after first failure to simplify debugging.
-
-```sh
-pip install -e . && pytest python/scripts/ -s -x
-```
-
-Linting:
-
-```sh
-pip install ruff
-ruff --format=github --select=E9,F63,F7,F82 --target-version=py37 python
-```
-
-Testing wheel builds locally:
-
-```sh
-pip install cibuildwheel
-cibuildwheel --platform linux
-```
-
-## JavaScript
-
-Node.JS:
-
-```sh
-npm install && node --test ./javascript/usearch.test.js
-npm publish
-```
-
-WebAssembly:
-
-```sh
-emcmake cmake -B ./build -DCMAKE_CXX_FLAGS="${CMAKE_CXX_FLAGS} -s TOTAL_MEMORY=64MB" && emmake make -C ./build
-node ./build/usearch.test.js
-```
-
-If you don't yet have `emcmake` installed:
-
-```sh
-git clone https://github.com/emscripten-core/emsdk.git && ./emsdk/emsdk install latest && ./emsdk/emsdk activate latest && source ./emsdk/emsdk_env.sh
-```
-
-## Rust
-
-```sh
-cargo test -p usearch
-cargo publish
-```
-
-## Java
-
-```sh
-gradle clean build
-java -cp . -Djava.library.path="$(pwd)/build/libs/usearch/shared" java/cloud/unum/usearch/Index.java
-```
-
-Or step by-step:
-
-```sh
-cs java/unum/cloud/usearch
-javac -h . Index.java
-
-# Ubuntu:
-g++ -c -fPIC -I${JAVA_HOME}/include -I${JAVA_HOME}/include/linux cloud_unum_usearch_Index.cpp -o cloud_unum_usearch_Index.o
-g++ -shared -fPIC -o libusearch_c.so cloud_unum_usearch_Index.o -lc
-
-# Windows
-g++ -c -I%JAVA_HOME%\include -I%JAVA_HOME%\include\win32 cloud_unum_usearch_Index.cpp -o cloud_unum_usearch_Index.o
-g++ -shared -o USearchJNI.dll cloud_unum_usearch_Index.o -Wl,--add-stdcall-alias
-
-# MacOS
-g++ -std=c++11 -c -fPIC \
-    -I../../../../include \
-    -I../../../../fp16/include \
-    -I../../../../simsimd/include \
-    -I${JAVA_HOME}/include -I${JAVA_HOME}/include/darwin cloud_unum_usearch_Index.cpp -o cloud_unum_usearch_Index.o
-g++ -dynamiclib -o libusearch.dylib cloud_unum_usearch_Index.o -lc
-# Run linking to that directory
-java -cp . -Djava.library.path="$(pwd)/java/cloud/unum/usearch/" Index.java
-java -cp . -Djava.library.path="$(pwd)/java" cloud.unum.usearch.Index
-```
-
-## Objective-C and Swift
-
-```sh
-swift build
-swift test -v
-```
-
-## C 99
-
-There are a few ways to compile the C 99 USearch SDK.
-Using the Makefile, specifying the targets you need:
-
-```sh
-cmake -B ./build_release -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DUSEARCH_USE_OPENMP=1 -DUSEARCH_USE_SIMSIMD=1 
-cmake --build ./build_release --config Release -j
-./build_release/test_c
-# On Windows:
-.\build_release\test_c.exe
-```
-
-## GoLang
-
-GoLang bindings are based on C.
-So one should first compile the C library, link it with GoLang, and only then run tests.
-
-```sh
-cmake -B ./build_release -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DUSEARCH_USE_OPENMP=1 -DUSEARCH_USE_SIMSIMD=1 
-cmake --build ./build_release --config Release -j
-mv ./c/libusearch_c.so ./golang/
-cp ./c/usearch.h ./golang/
-cd golang && go test -v ; cd ..
-```
-
-## Wolfram
-
-```sh
-brew install --cask wolfram-engine
-```
-
-## Docker
-
-```sh
-docker build -t unum/usearch . && docker run unum/usearch
-```
-
-For multi-architecture builds and publications:
-
-```sh
-version=$(cat VERSION)
-docker buildx create --use &&
-    docker login &&
-    docker buildx build \
-        --platform "linux/amd64,linux/arm64" \
-        --build-arg version=$version \
-        --file Dockerfile \
-        --tag unum/usearch:$version \
-        --tag unum/usearch:latest \
-        --push .
-```
-
-## Sub-Modules
-
-Extending metrics in SimSIMD:
-
-```sh
-git push --set-upstream https://github.com/ashvardanian/simsimd.git HEAD:main
-```

package/simsimd/.clang-format

@@ -1,10 +0,0 @@
-Language: Cpp
-BasedOnStyle:  LLVM
-IndentWidth: 4
-TabWidth: 4
-NamespaceIndentation: None
-ColumnLimit: 120
-ReflowComments: true
-UseTab: Never
-PointerAlignment: Left
-AllowShortCaseLabelsOnASingleLine: true