usearch 2.13.5 → 2.15.0

package/README.md

@@ -1,7 +1,7 @@
 <h1 align="center">USearch</h1>
 <h3 align="center">
 Smaller & <a href="https://www.unum.cloud/blog/2023-11-07-scaling-vector-search-with-intel">Faster</a> Single-File<br/>
-Similarity Search Engine for <a href="https://github.com/ashvardanian/simsimd">Vectors</a> & 🔜 <a href="https://github.com/ashvardanian/stringzilla">Texts</a>
+Similarity Search & Clustering Engine for <a href="https://github.com/ashvardanian/simsimd">Vectors</a> & 🔜 <a href="https://github.com/ashvardanian/stringzilla">Texts</a>
 </h3>
 <br/>
 
@@ -71,13 +71,10 @@ Linux • MacOS • Windows • iOS • WebAssembly •
 
 __Technical Insights__ and related articles:
 
-- [Uses Horner's method for polynomial approximations, beating GCC 12 by 119x](https://ashvardanian.com/posts/gcc-12-vs-avx512fp16/).
 - [Uses Arm SVE and x86 AVX-512's masked loads to eliminate tail `for`-loops](https://ashvardanian.com/posts/simsimd-faster-scipy/#tails-of-the-past-the-significance-of-masked-loads).
-- [Uses AVX-512 FP16 for half-precision operations, that few compilers vectorize](https://ashvardanian.com/posts/simsimd-faster-scipy/#the-challenge-of-f16).
-- [Substitutes LibC's `sqrt` calls with bithacks using Jan Kadlec's constant](https://ashvardanian.com/posts/simsimd-faster-scipy/#bonus-section-bypassing-sqrt-and-libc-dependencies).
+- [Uses Horner's method for polynomial approximations, beating GCC 12 by 119x](https://ashvardanian.com/posts/gcc-12-vs-avx512fp16/).
 - [For every language implements a custom separate binding](https://ashvardanian.com/posts/porting-cpp-library-to-ten-languages/).
-- [For Python avoids slow PyBind11, and even `PyArg_ParseTuple` for speed](https://ashvardanian.com/posts/pybind11-cpython-tutorial/).
-- [For JavaScript uses typed arrays and NAPI for zero-copy calls](https://ashvardanian.com/posts/javascript-ai-vector-search/).
+
 
 ## Comparison with FAISS
 
@@ -119,17 +116,15 @@ USearch is compact and broadly compatible without sacrificing performance, prima
 Base functionality is identical to FAISS, and the interface must be familiar if you have ever investigated Approximate Nearest Neighbors search:
 
 ```py
-# pip install numpy usearch
+# pip install usearch
 
 import numpy as np
 from usearch.index import Index
 
-index = Index(ndim=3)
-
-vector = np.array([0.2, 0.6, 0.4])
-index.add(42, vector)
-
-matches = index.search(vector, 10)
+index = Index(ndim=3)               # Default settings for 3D vectors
+vector = np.array([0.2, 0.6, 0.4])  # Can be a matrix for batch operations
+index.add(42, vector)               # Add one or many vectors in parallel
+matches = index.search(vector, 10)  # Find 10 nearest neighbors
 
 assert matches[0].key == 42
 assert matches[0].distance <= 0.001
@@ -137,13 +132,13 @@ assert np.allclose(index[42], vector, atol=0.1) # Ensure high tolerance in mixed
 ```
 
 More settings are always available, and the API is designed to be as flexible as possible.
-The default storage/quantization level is hardware-dependant for efficiency, but `f16` is recommended for most modern CPUs.
+The default storage/quantization level is hardware-dependant for efficiency, but `bf16` is recommended for most modern CPUs.
 
 ```py
 index = Index(
     ndim=3, # Define the number of dimensions in input vectors
     metric='cos', # Choose 'l2sq', 'ip', 'haversine' or other metric, default = 'cos'
-    dtype='f16', # Store as 'f64', 'f32', 'f16', 'i8', 'b1'..., default = None
+    dtype='bf16', # Store as 'f64', 'f32', 'f16', 'i8', 'b1'..., default = None
     connectivity=16, # Optional: Limit number of neighbors per graph node
     expansion_add=128, # Optional: Control the recall of indexing
     expansion_search=64, # Optional: Control the quality of the search
@@ -549,7 +544,7 @@ doi = {10.5281/zenodo.7949416},
 author = {Vardanian, Ash},
 title = {{USearch by Unum Cloud}},
 url = {https://github.com/unum-cloud/usearch},
-version = {2.13.5},
+version = {2.15.0},
 year = {2023},
 month = oct,
 }

package/cpp/bench.cpp

@@ -468,6 +468,7 @@ struct args_t {
 
     bool big = false;
 
+    bool quantize_bf16 = false;
     bool quantize_f16 = false;
     bool quantize_i8 = false;
     bool quantize_b1 = false;
@@ -500,6 +501,8 @@ struct args_t {
     }
 
     scalar_kind_t quantization() const noexcept {
+        if (quantize_bf16)
+            return scalar_kind_t::bf16_k;
         if (quantize_f16)
             return scalar_kind_t::f16_k;
         if (quantize_i8)
@@ -611,6 +614,7 @@ int main(int argc, char** argv) {
         (option("--rows-skip") & value("integer", args.vectors_to_skip)).doc("Number of vectors to skip"),
         (option("--rows-take") & value("integer", args.vectors_to_take)).doc("Number of vectors to take"),
         ( //
+            option("-bf16", "--bf16quant").set(args.quantize_bf16).doc("Enable `bf16_t` quantization") |
             option("-f16", "--f16quant").set(args.quantize_f16).doc("Enable `f16_t` quantization") |
             option("-i8", "--i8quant").set(args.quantize_i8).doc("Enable `i8_t` quantization") |
             option("-b1", "--b1quant").set(args.quantize_b1).doc("Enable `b1x8_t` quantization")),

package/include/usearch/index.hpp

@@ -8,8 +8,8 @@
 #define UNUM_USEARCH_HPP
 
 #define USEARCH_VERSION_MAJOR 2
-#define USEARCH_VERSION_MINOR 13
-#define USEARCH_VERSION_PATCH 5
+#define USEARCH_VERSION_MINOR 15
+#define USEARCH_VERSION_PATCH 0
 
 // Inferring C++ version
 // https://stackoverflow.com/a/61552074
@@ -2870,16 +2870,16 @@ class index_gt {
         result.computed_distances = context.computed_distances;
         result.visited_members = context.iteration_cycles;
 
-        // If we are updating the entry node itself, it won't contain any neighbors,
-        // so we should traverse a level down to find the closest match.
-        if (updated_node_level == max_level_copy)
-            updated_node_level--;
-
         // Go down the level, tracking only the closest match;
         // It may even be equal to the `updated_slot`
-        compressed_slot_t closest_slot = search_for_one_( //
-            value, metric, prefetch,                      //
-            entry_slot_copy, max_level_copy, updated_node_level, context);
+        compressed_slot_t closest_slot =
+            // If we are updating the entry node itself, it won't contain any neighbors,
+            // so we should traverse a level down to find the closest match.
+            updated_node_level == max_level_copy //
+                ? entry_slot_copy
+                : search_for_one_(             //
+                      value, metric, prefetch, //
+                      entry_slot_copy, max_level_copy, updated_node_level, context);
 
         // From `updated_node_level` down - perform proper extensive search
         for (level_t level = (std::min)(updated_node_level, max_level_copy); level >= 0; --level) {
@@ -2943,7 +2943,7 @@ class index_gt {
             config.expansion = default_expansion_search();
 
         // Using references is cleaner, but would result in UBSan false positives
-        context_t* context_ptr = contexts_.data() + config.thread;
+        context_t* context_ptr = contexts_.data() ? contexts_.data() + config.thread : nullptr;
         top_candidates_t* top_ptr = context_ptr ? &context_ptr->top_candidates : nullptr;
         search_result_t result{*this, top_ptr};
         if (!nodes_count_.load(std::memory_order_relaxed))
@@ -3697,6 +3697,7 @@ class index_gt {
     inline neighbors_ref_t neighbors_base_(node_t node) const noexcept { return {node.neighbors_tape()}; }
 
     inline neighbors_ref_t neighbors_non_base_(node_t node, level_t level) const noexcept {
+        usearch_assert_m(level > 0 && level <= node.level(), "Linking to missing level");
         return {node.neighbors_tape() + pre_.neighbors_base_bytes + (level - 1) * pre_.neighbors_bytes};
     }
 

package/include/usearch/index_dense.hpp

@@ -950,7 +950,7 @@ class index_dense_gt {
 
     void reserve(index_limits_t limits) {
         if (!try_reserve(limits))
-            throw std::bad_alloc();
+            __usearch_raise_runtime_error("failed to reserve memory");
     }
 
     /**
@@ -2240,6 +2240,7 @@ class index_dense_gt {
         case scalar_kind_t::f64_k: return make_casts_<f64_t>();
         case scalar_kind_t::f32_k: return make_casts_<f32_t>();
         case scalar_kind_t::f16_k: return make_casts_<f16_t>();
+        case scalar_kind_t::bf16_k: return make_casts_<bf16_t>();
         case scalar_kind_t::i8_k: return make_casts_<i8_t>();
         case scalar_kind_t::b1x8_k: return make_casts_<b1x8_t>();
         default: return {};

package/include/usearch/index_plugins.hpp

@@ -70,20 +70,10 @@ struct uuid_t {
 };
 
 class f16_bits_t;
+class bf16_bits_t;
 
-#if !USEARCH_USE_FP16LIB
-#if USEARCH_USE_SIMSIMD
-using f16_native_t = simsimd_f16_t;
-#elif defined(USEARCH_DEFINED_ARM)
-using f16_native_t = __fp16;
-#else
-using f16_native_t = _Float16;
-#endif
-using f16_t = f16_native_t;
-#else
-using f16_native_t = void;
 using f16_t = f16_bits_t;
-#endif
+using bf16_t = bf16_bits_t;
 
 using f64_t = double;
 using f32_t = float;
@@ -132,6 +122,7 @@ enum class scalar_kind_t : std::uint8_t {
     b1x8_k = 1,
     u40_k = 2,
     uuid_k = 3,
+    bf16_k = 4,
     // Common:
     f64_k = 10,
     f32_k = 11,
@@ -148,12 +139,6 @@ enum class scalar_kind_t : std::uint8_t {
     i8_k = 23,
 };
 
-enum class prefetching_kind_t {
-    none_k,
-    cpu_k,
-    io_uring_k,
-};
-
 template <typename scalar_at> scalar_kind_t scalar_kind() noexcept {
     if (std::is_same<scalar_at, b1x8_t>())
         return scalar_kind_t::b1x8_k;
@@ -167,6 +152,8 @@ template <typename scalar_at> scalar_kind_t scalar_kind() noexcept {
         return scalar_kind_t::f32_k;
     if (std::is_same<scalar_at, f16_t>())
         return scalar_kind_t::f16_k;
+    if (std::is_same<scalar_at, bf16_t>())
+        return scalar_kind_t::bf16_k;
     if (std::is_same<scalar_at, i8_t>())
         return scalar_kind_t::i8_k;
     if (std::is_same<scalar_at, u64_t>())
@@ -208,6 +195,7 @@ inline std::size_t bits_per_scalar(scalar_kind_t scalar_kind) noexcept {
     switch (scalar_kind) {
     case scalar_kind_t::uuid_k: return 128;
     case scalar_kind_t::u40_k: return 40;
+    case scalar_kind_t::bf16_k: return 16;
     case scalar_kind_t::b1x8_k: return 1;
     case scalar_kind_t::u64_k: return 64;
     case scalar_kind_t::i64_k: return 64;
@@ -229,6 +217,7 @@ inline std::size_t bits_per_scalar_word(scalar_kind_t scalar_kind) noexcept {
     switch (scalar_kind) {
     case scalar_kind_t::uuid_k: return 128;
     case scalar_kind_t::u40_k: return 40;
+    case scalar_kind_t::bf16_k: return 16;
     case scalar_kind_t::b1x8_k: return 8;
     case scalar_kind_t::u64_k: return 64;
     case scalar_kind_t::i64_k: return 64;
@@ -250,6 +239,7 @@ inline char const* scalar_kind_name(scalar_kind_t scalar_kind) noexcept {
     switch (scalar_kind) {
     case scalar_kind_t::uuid_k: return "uuid";
     case scalar_kind_t::u40_k: return "u40";
+    case scalar_kind_t::bf16_k: return "bf16";
     case scalar_kind_t::b1x8_k: return "b1x8";
     case scalar_kind_t::u64_k: return "u64";
     case scalar_kind_t::i64_k: return "i64";
@@ -291,10 +281,14 @@ inline expected_gt<scalar_kind_t> scalar_kind_from_name(char const* name, std::s
         parsed.result = scalar_kind_t::f64_k;
     else if (str_equals(name, len, "f16"))
         parsed.result = scalar_kind_t::f16_k;
+    else if (str_equals(name, len, "bf16"))
+        parsed.result = scalar_kind_t::bf16_k;
     else if (str_equals(name, len, "i8"))
         parsed.result = scalar_kind_t::i8_k;
+    else if (str_equals(name, len, "b1"))
+        parsed.result = scalar_kind_t::b1x8_k;
     else
-        parsed.failed("Unknown type, choose: f32, f16, f64, i8");
+        parsed.failed("Unknown type, choose: f64, f32, f16, bf16, i8, b1");
     return parsed;
 }
 
@@ -327,29 +321,76 @@ inline expected_gt<metric_kind_t> metric_from_name(char const* name, std::size_t
                       "tanimoto, sorensen");
     return parsed;
 }
-
 inline expected_gt<metric_kind_t> metric_from_name(char const* name) {
     return metric_from_name(name, std::strlen(name));
 }
 
+/**
+ *  @brief Convenience function to upcast a half-precision floating point number to a single-precision one.
+ */
 inline float f16_to_f32(std::uint16_t u16) noexcept {
-#if !USEARCH_USE_FP16LIB
+#if USEARCH_USE_FP16LIB
+    return fp16_ieee_to_fp32_value(u16);
+#elif USEARCH_USE_SIMSIMD
+    return simsimd_uncompress_f16(u16);
+#else
     f16_native_t f16;
     std::memcpy(&f16, &u16, sizeof(std::uint16_t));
     return float(f16);
-#else
-    return fp16_ieee_to_fp32_value(u16);
 #endif
 }
 
+/**
+ *  @brief Convenience function to downcast a single-precision floating point number to a half-precision one.
+ */
 inline std::uint16_t f32_to_f16(float f32) noexcept {
-#if !USEARCH_USE_FP16LIB
+#if USEARCH_USE_FP16LIB
+    return fp16_ieee_from_fp32_value(f32);
+#elif USEARCH_USE_SIMSIMD
+    return simsimd_compress_f16(f32);
+#else
     f16_native_t f16 = f16_native_t(f32);
     std::uint16_t u16;
     std::memcpy(&u16, &f16, sizeof(std::uint16_t));
     return u16;
+#endif
+}
+
+/**
+ *  @brief Convenience function to upcast a brain-floating point number to a single-precision one.
+ *  https://github.com/ashvardanian/SimSIMD/blob/ff51434d90c66f916e94ff05b24530b127aa4cff/include/simsimd/types.h#L395-L410
+ */
+inline float bf16_to_f32(std::uint16_t u16) noexcept {
+#if USEARCH_USE_SIMSIMD
+    return simsimd_uncompress_bf16(u16);
 #else
-    return fp16_ieee_from_fp32_value(f32);
+    union float_or_unsigned_int_t {
+        float f;
+        unsigned int i;
+    };
+    union float_or_unsigned_int_t result_union;
+    result_union.i = u16 << 16; // Zero extends the mantissa
+    return result_union.f;
+#endif
+}
+
+/**
+ *  @brief Convenience function to downcast a single-precision floating point number to a brain-floating point one.
+ *  https://github.com/ashvardanian/SimSIMD/blob/ff51434d90c66f916e94ff05b24530b127aa4cff/include/simsimd/types.h#L412-L425
+ */
+inline std::uint16_t f32_to_bf16(float f32) noexcept {
+#if USEARCH_USE_SIMSIMD
+    return simsimd_compress_bf16(f32);
+#else
+    union float_or_unsigned_int_t {
+        float f;
+        unsigned int i;
+    };
+    union float_or_unsigned_int_t value;
+    value.f = f32;
+    value.i >>= 16;
+    value.i &= 0xFFFF;
+    return (unsigned short)value.i;
 #endif
 }
 
@@ -412,6 +453,65 @@ class f16_bits_t {
     }
 };
 
+/**
+ *  @brief  Numeric type for brain-floating point half-precision floating point.
+ *          If hardware support isn't available, falls back to a hardware
+ *          agnostic in-software implementation.
+ */
+class bf16_bits_t {
+    std::uint16_t uint16_{};
+
+  public:
+    inline bf16_bits_t() noexcept : uint16_(0) {}
+    inline bf16_bits_t(bf16_bits_t&&) = default;
+    inline bf16_bits_t& operator=(bf16_bits_t&&) = default;
+    inline bf16_bits_t(bf16_bits_t const&) = default;
+    inline bf16_bits_t& operator=(bf16_bits_t const&) = default;
+
+    inline operator float() const noexcept { return bf16_to_f32(uint16_); }
+    inline explicit operator bool() const noexcept { return bf16_to_f32(uint16_) > 0.5f; }
+
+    inline bf16_bits_t(std::int8_t v) noexcept : uint16_(f32_to_bf16(v)) {}
+    inline bf16_bits_t(bool v) noexcept : uint16_(f32_to_bf16(v)) {}
+    inline bf16_bits_t(float v) noexcept : uint16_(f32_to_bf16(v)) {}
+    inline bf16_bits_t(double v) noexcept : uint16_(f32_to_bf16(static_cast<float>(v))) {}
+
+    inline bool operator<(bf16_bits_t const& other) const noexcept { return float(*this) < float(other); }
+
+    inline bf16_bits_t operator+(bf16_bits_t other) const noexcept { return {float(*this) + float(other)}; }
+    inline bf16_bits_t operator-(bf16_bits_t other) const noexcept { return {float(*this) - float(other)}; }
+    inline bf16_bits_t operator*(bf16_bits_t other) const noexcept { return {float(*this) * float(other)}; }
+    inline bf16_bits_t operator/(bf16_bits_t other) const noexcept { return {float(*this) / float(other)}; }
+    inline float operator+(float other) const noexcept { return float(*this) + other; }
+    inline float operator-(float other) const noexcept { return float(*this) - other; }
+    inline float operator*(float other) const noexcept { return float(*this) * other; }
+    inline float operator/(float other) const noexcept { return float(*this) / other; }
+    inline double operator+(double other) const noexcept { return float(*this) + other; }
+    inline double operator-(double other) const noexcept { return float(*this) - other; }
+    inline double operator*(double other) const noexcept { return float(*this) * other; }
+    inline double operator/(double other) const noexcept { return float(*this) / other; }
+
+    inline bf16_bits_t& operator+=(float v) noexcept {
+        uint16_ = f32_to_bf16(v + bf16_to_f32(uint16_));
+        return *this;
+    }
+
+    inline bf16_bits_t& operator-=(float v) noexcept {
+        uint16_ = f32_to_bf16(v - bf16_to_f32(uint16_));
+        return *this;
+    }
+
+    inline bf16_bits_t& operator*=(float v) noexcept {
+        uint16_ = f32_to_bf16(v * bf16_to_f32(uint16_));
+        return *this;
+    }
+
+    inline bf16_bits_t& operator/=(float v) noexcept {
+        uint16_ = f32_to_bf16(v / bf16_to_f32(uint16_));
+        return *this;
+    }
+};
+
 /**
  *  @brief  An STL-based executor or a "thread-pool" for parallel execution.
  *          Isn't efficient for small batches, as it recreates the threads on every call.
@@ -936,6 +1036,10 @@ template <> struct cast_gt<f16_bits_t, f16_bits_t> {
     static bool try_(byte_t const*, std::size_t, byte_t*) noexcept { return false; }
 };
 
+template <> struct cast_gt<bf16_bits_t, bf16_bits_t> {
+    static bool try_(byte_t const*, std::size_t, byte_t*) noexcept { return false; }
+};
+
 template <> struct cast_gt<i8_t, i8_t> {
     static bool try_(byte_t const*, std::size_t, byte_t*) noexcept { return false; }
 };
@@ -1008,19 +1112,23 @@ template <typename to_scalar_at> struct cast_from_i8_gt {
     }
 };
 
-template <> struct cast_gt<i8_t, f16_t> : public cast_from_i8_gt<f16_t> {};
+template <> struct cast_gt<i8_t, f16_bits_t> : public cast_from_i8_gt<f16_t> {};
+template <> struct cast_gt<i8_t, bf16_bits_t> : public cast_from_i8_gt<bf16_t> {};
 template <> struct cast_gt<i8_t, f32_t> : public cast_from_i8_gt<f32_t> {};
 template <> struct cast_gt<i8_t, f64_t> : public cast_from_i8_gt<f64_t> {};
 
-template <> struct cast_gt<f16_t, i8_t> : public cast_to_i8_gt<f16_t> {};
+template <> struct cast_gt<f16_bits_t, i8_t> : public cast_to_i8_gt<f16_t> {};
+template <> struct cast_gt<bf16_bits_t, i8_t> : public cast_to_i8_gt<bf16_t> {};
 template <> struct cast_gt<f32_t, i8_t> : public cast_to_i8_gt<f32_t> {};
 template <> struct cast_gt<f64_t, i8_t> : public cast_to_i8_gt<f64_t> {};
 
-template <> struct cast_gt<b1x8_t, f16_t> : public cast_from_b1x8_gt<f16_t> {};
+template <> struct cast_gt<b1x8_t, f16_bits_t> : public cast_from_b1x8_gt<f16_t> {};
+template <> struct cast_gt<b1x8_t, bf16_bits_t> : public cast_from_b1x8_gt<bf16_t> {};
 template <> struct cast_gt<b1x8_t, f32_t> : public cast_from_b1x8_gt<f32_t> {};
 template <> struct cast_gt<b1x8_t, f64_t> : public cast_from_b1x8_gt<f64_t> {};
 
-template <> struct cast_gt<f16_t, b1x8_t> : public cast_to_b1x8_gt<f16_t> {};
+template <> struct cast_gt<f16_bits_t, b1x8_t> : public cast_to_b1x8_gt<f16_t> {};
+template <> struct cast_gt<bf16_bits_t, b1x8_t> : public cast_to_b1x8_gt<bf16_t> {};
 template <> struct cast_gt<f32_t, b1x8_t> : public cast_to_b1x8_gt<f32_t> {};
 template <> struct cast_gt<f64_t, b1x8_t> : public cast_to_b1x8_gt<f64_t> {};
 
@@ -1602,6 +1710,7 @@ class metric_punned_t {
         case scalar_kind_t::f32_k: datatype = simsimd_datatype_f32_k; break;
         case scalar_kind_t::f64_k: datatype = simsimd_datatype_f64_k; break;
         case scalar_kind_t::f16_k: datatype = simsimd_datatype_f16_k; break;
+        case scalar_kind_t::bf16_k: datatype = simsimd_datatype_bf16_k; break;
         case scalar_kind_t::i8_k: datatype = simsimd_datatype_i8_k; break;
         case scalar_kind_t::b1x8_k: datatype = simsimd_datatype_b8_k; break;
         default: break;
@@ -1654,9 +1763,10 @@ class metric_punned_t {
         switch (metric_kind_) {
         case metric_kind_t::ip_k: {
             switch (scalar_kind_) {
-            case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<f32_t>>; break;
-            case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<f16_t, f32_t>>; break;
+            case scalar_kind_t::bf16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<bf16_t, f32_t>>; break;
             case scalar_kind_t::i8_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<i8_t, f32_t>>; break;
+            case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<f16_t, f32_t>>; break;
+            case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<f32_t>>; break;
             case scalar_kind_t::f64_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_ip_gt<f64_t>>; break;
             default: metric_ptr_ = 0; break;
             }
@@ -1664,9 +1774,10 @@ class metric_punned_t {
         }
         case metric_kind_t::cos_k: {
             switch (scalar_kind_) {
-            case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<f32_t>>; break;
-            case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<f16_t, f32_t>>; break;
+            case scalar_kind_t::bf16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<bf16_t, f32_t>>; break;
             case scalar_kind_t::i8_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<i8_t, f32_t>>; break;
+            case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<f16_t, f32_t>>; break;
+            case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<f32_t>>; break;
             case scalar_kind_t::f64_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_cos_gt<f64_t>>; break;
             default: metric_ptr_ = 0; break;
             }
@@ -1674,9 +1785,10 @@ class metric_punned_t {
         }
         case metric_kind_t::l2sq_k: {
             switch (scalar_kind_) {
-            case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<f32_t>>; break;
-            case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<f16_t, f32_t>>; break;
+            case scalar_kind_t::bf16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<bf16_t, f32_t>>; break;
             case scalar_kind_t::i8_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<i8_t, f32_t>>; break;
+            case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<f16_t, f32_t>>; break;
+            case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<f32_t>>; break;
             case scalar_kind_t::f64_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_l2sq_gt<f64_t>>; break;
             default: metric_ptr_ = 0; break;
             }
@@ -1684,6 +1796,9 @@ class metric_punned_t {
         }
         case metric_kind_t::pearson_k: {
             switch (scalar_kind_) {
+            case scalar_kind_t::bf16_k:
+                metric_ptr_ = (uptr_t)&equidimensional_<metric_pearson_gt<bf16_t, f32_t>>;
+                break;
             case scalar_kind_t::i8_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_pearson_gt<i8_t, f32_t>>; break;
             case scalar_kind_t::f16_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_pearson_gt<f16_t, f32_t>>; break;
             case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_pearson_gt<f32_t>>; break;
@@ -1694,7 +1809,8 @@ class metric_punned_t {
         }
         case metric_kind_t::haversine_k: {
             switch (scalar_kind_) {
-            case scalar_kind_t::f16_k: metric_ptr_ = 0; break; //< Having half-precision 2D coordinates is a bit silly.
+            case scalar_kind_t::bf16_k: metric_ptr_ = 0; break; //< Half-precision 2D vectors are silly.
+            case scalar_kind_t::f16_k: metric_ptr_ = 0; break;  //< Half-precision 2D vectors are silly.
             case scalar_kind_t::f32_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_haversine_gt<f32_t>>; break;
             case scalar_kind_t::f64_k: metric_ptr_ = (uptr_t)&equidimensional_<metric_haversine_gt<f64_t>>; break;
             default: metric_ptr_ = 0; break;
@@ -1703,6 +1819,9 @@ class metric_punned_t {
         }
         case metric_kind_t::divergence_k: {
             switch (scalar_kind_) {
+            case scalar_kind_t::bf16_k:
+                metric_ptr_ = (uptr_t)&equidimensional_<metric_divergence_gt<bf16_t, f32_t>>;
+                break;
             case scalar_kind_t::f16_k:
                 metric_ptr_ = (uptr_t)&equidimensional_<metric_divergence_gt<f16_t, f32_t>>;
                 break;
@@ -1962,7 +2081,7 @@ class flat_hash_multi_set_gt {
         // Allocate new memory
         data_ = (char*)allocator_t{}.allocate(other.buckets_ * bytes_per_bucket());
         if (!data_)
-            throw std::bad_alloc();
+            __usearch_raise_runtime_error("failed memory allocation");
 
         // Copy metadata
         buckets_ = other.buckets_;
@@ -2002,7 +2121,7 @@ class flat_hash_multi_set_gt {
         // Allocate new memory
         data_ = (char*)allocator_t{}.allocate(other.buckets_ * bytes_per_bucket());
         if (!data_)
-            throw std::bad_alloc();
+            __usearch_raise_runtime_error("failed memory allocation");
 
         // Copy metadata
         buckets_ = other.buckets_;
@@ -2375,7 +2494,7 @@ class flat_hash_multi_set_gt {
 
     void reserve(std::size_t capacity) {
         if (!try_reserve(capacity))
-            throw std::bad_alloc();
+            __usearch_raise_runtime_error("failed to reserve memory");
     }
 
     bool try_emplace(element_t const& element) noexcept {

package/javascript/dist/cjs/usearch.d.ts

@@ -29,6 +29,7 @@ export declare enum ScalarKind {
     F32 = "f32",
     F64 = "f64",
     F16 = "f16",
+    BF16 = "bf16",
     I8 = "i8",
     B1 = "b1"
 }

package/javascript/dist/cjs/usearch.js

@@ -74,6 +74,7 @@ var ScalarKind;
     ScalarKind["F32"] = "f32";
     ScalarKind["F64"] = "f64";
     ScalarKind["F16"] = "f16";
+    ScalarKind["BF16"] = "bf16";
     ScalarKind["I8"] = "i8";
     ScalarKind["B1"] = "b1";
 })(ScalarKind || (exports.ScalarKind = ScalarKind = {}));

package/javascript/dist/esm/usearch.d.ts

@@ -29,6 +29,7 @@ export declare enum ScalarKind {
     F32 = "f32",
     F64 = "f64",
     F16 = "f16",
+    BF16 = "bf16",
     I8 = "i8",
     B1 = "b1"
 }

package/javascript/dist/esm/usearch.js

@@ -33,6 +33,7 @@ export var ScalarKind;
     ScalarKind["F32"] = "f32";
     ScalarKind["F64"] = "f64";
     ScalarKind["F16"] = "f16";
+    ScalarKind["BF16"] = "bf16";
     ScalarKind["I8"] = "i8";
     ScalarKind["B1"] = "b1";
 })(ScalarKind || (ScalarKind = {}));

package/javascript/usearch.ts

@@ -70,6 +70,7 @@ export enum ScalarKind {
   F32 = "f32",
   F64 = "f64",
   F16 = "f16",
+  BF16 = "bf16",
   I8 = "i8",
   B1 = "b1",
 }
@@ -610,12 +611,12 @@ function exactSearch(
 }
 
 const usearch = {
-    Index,
-    MetricKind,
-    ScalarKind,
-    Matches,
-    BatchMatches,
-    exactSearch,
+  Index,
+  MetricKind,
+  ScalarKind,
+  Matches,
+  BatchMatches,
+  exactSearch,
 };
 export default usearch;
 

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "usearch",
-    "version": "2.13.5",
+    "version": "2.15.0",
     "description": "Smaller & Faster Single-File Vector Search Engine from Unum",
     "author": "Ash Vardanian (https://ashvardanian.com/)",
     "license": "Apache 2.0",