usearch 2.8.6 → 2.8.8

package/setup.py

@@ -5,19 +5,49 @@ from setuptools import setup
 
 from pybind11.setup_helpers import Pybind11Extension
 
-
 compile_args = []
 link_args = []
 macros_args = []
 
-def is_gcc():
+
+def get_bool_env(name: str, preference: bool) -> bool:
+    return os.environ.get(name, "1" if preference else "0") == "1"
+
+
+def get_bool_env_w_name(name: str, preference: bool) -> bool:
+    return name, get_bool_env(name, preference)
+
+
+def get_is_gcc():
     try:
-        compiler_version = subprocess.check_output(["c++", "--version"], universal_newlines=True)
+        compiler_version = subprocess.check_output(
+            ["c++", "--version"], universal_newlines=True
+        )
         return "gcc" in compiler_version.lower()
     except Exception:
         return False
 
-if sys.platform == "linux":
+
+# Check the environment variables
+is_linux: bool = sys.platform == "linux"
+is_macos: bool = sys.platform == "darwin"
+is_windows: bool = sys.platform == "win32"
+
+prefer_simsimd: bool = is_linux or is_macos
+prefer_fp16lib: bool = True
+prefer_openmp: bool = is_linux and get_is_gcc()
+
+use_simsimd: bool = get_bool_env("USEARCH_USE_SIMSIMD", prefer_simsimd)
+use_fp16lib: bool = get_bool_env("USEARCH_USE_FP16LIB", prefer_fp16lib)
+use_openmp: bool = get_bool_env("USEARCH_USE_OPENMP", prefer_openmp)
+
+
+# Common arguments for all platforms
+macros_args.append(("USEARCH_USE_OPENMP", "1" if use_openmp else "0"))
+macros_args.append(("USEARCH_USE_SIMSIMD", "1" if use_simsimd else "0"))
+macros_args.append(("USEARCH_USE_FP16LIB", "1" if use_fp16lib else "0"))
+
+if is_linux:
     compile_args.append("-std=c++17")
     compile_args.append("-O3")  # Maximize performance
     compile_args.append("-ffast-math")  # Maximize floating-point performance
@@ -27,17 +57,21 @@ if sys.platform == "linux":
     # Simplify debugging, but the normal `-g` may make builds much longer!
     compile_args.append("-g1")
 
-    macros_args.append(("USEARCH_USE_NATIVE_F16", "0"))
-    macros_args.append(("USEARCH_USE_SIMSIMD", "1"))
-
-    if is_gcc():
-        macros_args.append(("USEARCH_USE_OPENMP", "1"))
+    if use_openmp:
         compile_args.append("-fopenmp")
         link_args.append("-lgomp")
-    else:
-        macros_args.append(("USEARCH_USE_OPENMP", "0"))
 
-if sys.platform == "darwin":
+    if use_simsimd:
+        macros_args.extend(
+            [
+                get_bool_env_w_name("SIMSIMD_TARGET_X86_AVX512", True),
+                get_bool_env_w_name("SIMSIMD_TARGET_ARM_SVE", True),
+                get_bool_env_w_name("SIMSIMD_TARGET_X86_AVX2", True),
+                get_bool_env_w_name("SIMSIMD_TARGET_ARM_NEON", True),
+            ]
+        )
+
+if is_macos:
     # MacOS 10.15 or higher is needed for `aligned_alloc` support.
     # https://github.com/unum-cloud/usearch/actions/runs/4975434891/jobs/8902603392
     compile_args.append("-mmacosx-version-min=10.15")
@@ -61,12 +95,34 @@ if sys.platform == "darwin":
     #     link_args.append("-lomp")
     #     macros_args.append(("USEARCH_USE_OPENMP", "1"))
 
-if sys.platform == "win32":
+    if use_simsimd:
+        macros_args.extend(
+            [
+                get_bool_env_w_name("SIMSIMD_TARGET_X86_AVX512", False),
+                get_bool_env_w_name("SIMSIMD_TARGET_ARM_SVE", False),
+                get_bool_env_w_name("SIMSIMD_TARGET_X86_AVX2", True),
+                get_bool_env_w_name("SIMSIMD_TARGET_ARM_NEON", True),
+            ]
+        )
+
+if is_windows:
     compile_args.append("/std:c++17")
     compile_args.append("/O2")
     compile_args.append("/fp:fast")  # Enable fast math for MSVC
     compile_args.append("/W1")  # Reduce warnings verbosity
 
+    # We don't actually want to use any SimSIMD stuff,
+    # as GCC attributes aren't compatible with MSVC
+    if use_simsimd:
+        macros_args.extend(
+            [
+                get_bool_env_w_name("SIMSIMD_TARGET_X86_AVX512", False),
+                get_bool_env_w_name("SIMSIMD_TARGET_ARM_SVE", False),
+                get_bool_env_w_name("SIMSIMD_TARGET_X86_AVX2", False),
+                get_bool_env_w_name("SIMSIMD_TARGET_ARM_NEON", False),
+            ]
+        )
+
 ext_modules = [
     Pybind11Extension(
         "usearch.compiled",
@@ -80,11 +136,16 @@ ext_modules = [
 __version__ = open("VERSION", "r").read().strip()
 __lib_name__ = "usearch"
 
-
 this_directory = os.path.abspath(os.path.dirname(__file__))
 with open(os.path.join(this_directory, "README.md")) as f:
     long_description = f.read()
 
+# Depending on the macros, adjust the include directories
+include_dirs = ["include"]
+if use_simsimd:
+    include_dirs.append("simsimd/include")
+if use_fp16lib:
+    include_dirs.append("fp16/include")
 
 setup(
     name=__lib_name__,
@@ -118,7 +179,7 @@ setup(
         "Topic :: Database :: Database Engines/Servers",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
     ],
-    include_dirs=["include", "fp16/include", "simsimd/include"],
+    include_dirs=include_dirs,
     ext_modules=ext_modules,
     install_requires=[
         "numpy",

package/wasmer.toml

@@ -1,6 +1,6 @@
 [package]
 name="unum/usearch"
-version="2.8.6"
+version="2.8.8"
 description="Smaller & Faster Single-File Vector Search Engine from Unum"
 license="Apache-2.0"
 readme="README.md"

package/. npmignore

@@ -1,14 +0,0 @@
-node_modules/
-.vscode/
-build/
-csharp/
-golang/
-java/
-objc/
-rust/
-swift/
-wolfram/
-python/
-docs/
-wasm/
-Package.swift

package/.gitignore

@@ -1,95 +0,0 @@
-# Ignore all files without an extension
-*
-!/**/
-!*.*
-
-# Temporary files
-.DS_Store
-*.fbin
-*.ibin
-datasets
-bin
-*.usearch
-.cache
-
-# C++ builds
-build
-build_release
-build_debug
-build_artifacts
-_deps
-CMakeCache.txt
-CMakeFiles
-cmake_install.cmake
-
-# Profiling with GProf and `perf` on Linux
-gmon.out
-perf.data
-
-# Python wrappers
-__pycache__
-*.egg-info
-dist/
-wheelhouse/
-
-# Python Environments
-venv/
-
-# JS wrappers
-package-lock.json
-node_modules/
-
-# Rust builds
-Cargo.lock
-target/
-
-# Java bindings
-.gradle
-*.class
-
-# ObjC and Swift
-.build
-.swiftpm
-
-# C# builds
-csharp/**/[Bb]in/
-csharp/**/[Oo]bj/
-csharp/lib
-csharp/packages
-
-# Prerequisites
-*.d
-
-# Compiled Object files
-*.slo
-*.lo
-*.o
-*.obj
-
-# Precompiled Headers
-*.gch
-*.pch
-
-# Compiled Dynamic libraries
-*.so
-*.dylib
-*.dll
-
-# Fortran module files
-*.mod
-*.smod
-
-# Allow golang go.mod
-!go.mod
-
-# Compiled Static libraries
-*.lai
-*.la
-*.a
-*.lib
-
-# Executables
-*.exe
-*.out
-*.app
-

package/.vscode/launch.json

@@ -1,181 +0,0 @@
-{
-    "version": "0.2.0",
-    "configurations": [
-        {
-            "name": "Unit Test C++",
-            "type": "cppdbg",
-            "request": "launch",
-            "program": "${workspaceFolder}/build_debug/test_cpp",
-            "cwd": "${workspaceFolder}",
-            "environment": [
-                {
-                    "name": "ASAN_OPTIONS",
-                    "value": "detect_leaks=0:atexit=1:strict_init_order=1:strict_string_checks=1:abort_on_error=0"
-                },
-                {
-                    "name": "LSAN_OPTIONS",
-                    "value": "verbosity=1:log_threads=1"
-                }
-            ],
-            "stopAtEntry": false,
-            "linux": {
-                "preLaunchTask": "Linux Build Debug",
-                "MIMode": "gdb"
-            },
-            "osx": {
-                "preLaunchTask": "MacOS Build Debug",
-                "MIMode": "lldb"
-            },
-            "windows": {
-                "preLaunchTask": "Windows Build Debug",
-                "type": "cppvsdbg",
-                "program": "${workspaceFolder}/build_debug/test_cpp.exe"
-            }
-        },
-        {
-            "name": "Unit Test C",
-            "type": "cppdbg",
-            "request": "launch",
-            "program": "${workspaceFolder}/build_debug/test_c",
-            "cwd": "${workspaceFolder}",
-            "environment": [
-                {
-                    "name": "ASAN_OPTIONS",
-                    "value": "detect_leaks=0:atexit=1:strict_init_order=1:strict_string_checks=1:abort_on_error=0"
-                },
-                {
-                    "name": "LSAN_OPTIONS",
-                    "value": "verbosity=1:log_threads=1"
-                }
-            ],
-            "stopAtEntry": false,
-            "linux": {
-                "preLaunchTask": "Linux Build Debug",
-                "MIMode": "gdb"
-            },
-            "osx": {
-                "preLaunchTask": "MacOS Build Debug",
-                "MIMode": "lldb"
-            },
-            "windows": {
-                "preLaunchTask": "Windows Build Debug",
-                "type": "cppvsdbg",
-                "program": "${workspaceFolder}/build_debug/test_c.exe"
-            }
-        },
-        {
-            "name": "Debug C++ on Wiki 1M @Cos",
-            "type": "cppdbg",
-            "request": "launch",
-            "program": "${workspaceFolder}/build_debug/bench_cpp",
-            "cwd": "${workspaceFolder}",
-            "args": [
-                "--vectors",
-                "datasets/wiki_1M/base.1M.fbin",
-                "--queries",
-                "datasets/wiki_1M/query.public.100K.fbin",
-                "--neighbors",
-                "datasets/wiki_1M/groundtruth.public.100K.ibin",
-                "--ip"
-            ],
-            "environment": [
-                {
-                    "name": "ASAN_OPTIONS",
-                    "value": "detect_leaks=0:atexit=1:strict_init_order=1:strict_string_checks=1"
-                }
-            ],
-            "stopAtEntry": false,
-            "linux": {
-                "preLaunchTask": "Linux Build Debug",
-                "MIMode": "gdb",
-                "environment": [
-                    {
-                        "name": "MALLOC_CHECK_",
-                        "value": "2"
-                    }
-                ]
-            },
-            "osx": {
-                "preLaunchTask": "MacOS Build Debug",
-                "MIMode": "lldb"
-            }
-        },
-        {
-            "name": "Debug C++ on Text-to-Image 1B @Cos",
-            "type": "cppdbg",
-            "request": "launch",
-            "program": "${workspaceFolder}/build_debug/bench_cpp",
-            "cwd": "${workspaceFolder}",
-            "args": [
-                "--vectors",
-                "datasets/t2i_1B/base.1B.fbin",
-                "--queries",
-                "datasets/t2i_1B/query.public.100K.fbin",
-                "--neighbors",
-                "datasets/t2i_1B/groundtruth.public.100K.ibin",
-                "--cos"
-            ],
-            "environment": [
-                {
-                    "name": "ASAN_OPTIONS",
-                    "value": "detect_leaks=0:atexit=1:strict_init_order=1:strict_string_checks=1"
-                }
-            ],
-            "stopAtEntry": false,
-            "linux": {
-                "preLaunchTask": "Linux Build Debug",
-                "MIMode": "gdb"
-            },
-            "osx": {
-                "preLaunchTask": "MacOS Build Debug",
-                "MIMode": "lldb"
-            }
-        },
-        {
-            "name": "Run C++ on Text-to-Image 1M @Cos",
-            "type": "cppdbg",
-            "request": "launch",
-            "program": "${workspaceFolder}/build_release/bench_cpp",
-            "cwd": "${workspaceFolder}",
-            "args": [
-                "--vectors",
-                "datasets/t2i_1M/base.1M.fbin",
-                "--queries",
-                "datasets/t2i_1M/query.public.100K.fbin",
-                "--neighbors",
-                "datasets/t2i_1M/groundtruth.public.100K.ibin",
-            ],
-            "stopAtEntry": false,
-            "preLaunchTask": "Linux Build Release",
-            "MIMode": "gdb"
-        },
-        {
-            "name": "Debug PyTest",
-            "type": "python",
-            "request": "launch",
-            "module": "pytest",
-            "console": "internalConsole",
-            "args": [
-                "${file}"
-            ],
-            "justMyCode": true
-        },
-        {
-            "name": "Debug Python Benchmark",
-            "type": "python",
-            "request": "launch",
-            "program": "python/scripts/bench.py",
-            "console": "internalConsole",
-            "args": [
-                "speed",
-                "--vectors",
-                "datasets/wiki_1M/base.1M.fbin",
-                "--queries",
-                "datasets/wiki_1M/query.public.100K.fbin",
-                "--neighbors",
-                "datasets/wiki_1M/groundtruth.public.100K.ibin",
-            ],
-            "justMyCode": true
-        }
-    ]
-}

package/.vscode/settings.json

@@ -1,180 +0,0 @@
-{
-  "files.associations": {
-    "array": "cpp",
-    "atomic": "cpp",
-    "hash_map": "cpp",
-    "hash_set": "cpp",
-    "barrier": "cpp",
-    "bit": "cpp",
-    "*.tcc": "cpp",
-    "bitset": "cpp",
-    "cctype": "cpp",
-    "chrono": "cpp",
-    "cinttypes": "cpp",
-    "clocale": "cpp",
-    "cmath": "cpp",
-    "codecvt": "cpp",
-    "compare": "cpp",
-    "complex": "cpp",
-    "concepts": "cpp",
-    "condition_variable": "cpp",
-    "csignal": "cpp",
-    "cstdarg": "cpp",
-    "cstddef": "cpp",
-    "cstdint": "cpp",
-    "cstdio": "cpp",
-    "cstdlib": "cpp",
-    "cstring": "cpp",
-    "ctime": "cpp",
-    "cwchar": "cpp",
-    "cwctype": "cpp",
-    "deque": "cpp",
-    "forward_list": "cpp",
-    "list": "cpp",
-    "map": "cpp",
-    "set": "cpp",
-    "string": "cpp",
-    "unordered_map": "cpp",
-    "unordered_set": "cpp",
-    "vector": "cpp",
-    "exception": "cpp",
-    "algorithm": "cpp",
-    "functional": "cpp",
-    "iterator": "cpp",
-    "memory": "cpp",
-    "memory_resource": "cpp",
-    "numeric": "cpp",
-    "optional": "cpp",
-    "random": "cpp",
-    "ratio": "cpp",
-    "regex": "cpp",
-    "string_view": "cpp",
-    "system_error": "cpp",
-    "tuple": "cpp",
-    "type_traits": "cpp",
-    "utility": "cpp",
-    "fstream": "cpp",
-    "initializer_list": "cpp",
-    "iomanip": "cpp",
-    "iosfwd": "cpp",
-    "iostream": "cpp",
-    "istream": "cpp",
-    "limits": "cpp",
-    "mutex": "cpp",
-    "new": "cpp",
-    "numbers": "cpp",
-    "ostream": "cpp",
-    "semaphore": "cpp",
-    "sstream": "cpp",
-    "stdexcept": "cpp",
-    "stop_token": "cpp",
-    "streambuf": "cpp",
-    "thread": "cpp",
-    "typeindex": "cpp",
-    "typeinfo": "cpp",
-    "valarray": "cpp",
-    "variant": "cpp",
-    "__bit_reference": "cpp",
-    "__bits": "cpp",
-    "__config": "cpp",
-    "__debug": "cpp",
-    "__errc": "cpp",
-    "__hash_table": "cpp",
-    "__locale": "cpp",
-    "__mutex_base": "cpp",
-    "__node_handle": "cpp",
-    "__nullptr": "cpp",
-    "__split_buffer": "cpp",
-    "__string": "cpp",
-    "__threading_support": "cpp",
-    "__tree": "cpp",
-    "__tuple": "cpp",
-    "any": "cpp",
-    "ios": "cpp",
-    "locale": "cpp",
-    "queue": "cpp",
-    "stack": "cpp",
-    "__memory": "cpp",
-    "filesystem": "cpp",
-    "__availability": "cpp",
-    "version": "cpp",
-    "future": "cpp",
-    "__verbose_abort": "cpp",
-    "shared_mutex": "cpp",
-    "ranges": "cpp",
-    "span": "cpp",
-    "format": "cpp",
-    "charconv": "cpp"
-  },
-  "cSpell.words": [
-    "allclose",
-    "arange",
-    "astype",
-    "Availible",
-    "bidict",
-    "BLAS",
-    "Cdecl",
-    "cflags",
-    "cibuildwheel",
-    "citerator",
-    "downcasted",
-    "Downcasting",
-    "dtype",
-    "DUSEARCH",
-    "emcmake",
-    "equi",
-    "equidimensional",
-    "FAISS",
-    "fbin",
-    "groundtruth",
-    "hashable",
-    "HNSW",
-    "hnswlib",
-    "ibin",
-    "jaccard",
-    "libusearch",
-    "linalg",
-    "longlong",
-    "memmap",
-    "Napi",
-    "ndarray",
-    "ndim",
-    "Numba",
-    "numpy",
-    "OPENMP",
-    "preprocess",
-    "Println",
-    "pytest",
-    "Quickstart",
-    "rtype",
-    "SIMD",
-    "simsimd",
-    "SLOC",
-    "Sonatype",
-    "sorensen",
-    "Struct",
-    "tanimoto",
-    "tqdm",
-    "uninitialize",
-    "unumusearch",
-    "usearch",
-    "usecases",
-    "Vardanian",
-    "vectorize",
-    "Xunit"
-  ],
-  "autoDocstring.docstringFormat": "sphinx",
-  "java.configuration.updateBuildConfiguration": "interactive",
-  "python.testing.pytestArgs": ["python"],
-  "python.analysis.diagnosticSeverityOverrides": {
-    "reportMissingImports": "none"
-  },
-  "python.testing.unittestEnabled": false,
-  "python.testing.pytestEnabled": true,
-  "[go]": {
-    "editor.insertSpaces": true,
-    "editor.formatOnSave": true,
-    "editor.defaultFormatter": "golang.go"
-  },
-  "dotnet.defaultSolution": "csharp/Cloud.Unum.USearch.sln"
-}

package/.vscode/tasks.json

@@ -1,71 +0,0 @@
-{
-    "version": "2.0.0",
-    "tasks": [
-        {
-            "label": "Linux Build Debug",
-            "command": "cmake -DCMAKE_CXX_COMPILER=gcc-12 -DCMAKE_CXX_COMPILER=g++-12 -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DCMAKE_BUILD_TYPE=Debug -B ./build_debug && cmake --build ./build_debug --config Debug",
-            "args": [],
-            "type": "shell",
-            "problemMatcher": [
-                "$gcc"
-            ]
-        },
-        {
-            "label": "Linux Build Release",
-            "command": "cmake -DCMAKE_CXX_COMPILER=gcc-12 -DCMAKE_CXX_COMPILER=g++-12 -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DCMAKE_BUILD_TYPE=Release -B ./build_release && cmake --build ./build_release --config RelWithDebInfo",
-            "args": [],
-            "type": "shell",
-            "problemMatcher": [
-                "$gcc"
-            ]
-        },
-        {
-            "label": "MacOS Build Debug",
-            "command": "cmake -DCMAKE_C_COMPILER=/opt/homebrew/opt/llvm/bin/clang -DCMAKE_CXX_COMPILER=/opt/homebrew/opt/llvm/bin/clang++ -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DCMAKE_BUILD_TYPE=Debug -B ./build_debug && cmake --build ./build_debug --config Debug",
-            "args": [],
-            "type": "shell",
-        },
-        {
-            "label": "MacOS Build Release",
-            "command": "cmake -DCMAKE_C_COMPILER=/opt/homebrew/opt/llvm/bin/clang -DCMAKE_CXX_COMPILER=/opt/homebrew/opt/llvm/bin/clang++ -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DCMAKE_BUILD_TYPE=Release -B ./build_release && cmake --build ./build_release --config RelWithDebInfo",
-            "args": [],
-            "type": "shell"
-        },
-        {
-            "label": "Windows Build Debug",
-            "command": "cmake -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DCMAKE_BUILD_TYPE=Debug -B ./build_debug && cmake --build ./build_debug --config Debug",
-            "args": [],
-            "type": "shell",
-            "problemMatcher": [
-                "$msCompile"
-            ],
-            "options": {
-                "shell": {
-                    "executable": "cmd.exe",
-                    "args": [
-                        "/d",
-                        "/c"
-                    ]
-                }
-            }
-        },
-        {
-            "label": "Windows Build Release",
-            "command": "cmake -DUSEARCH_BUILD_LIB_C=1 -DUSEARCH_BUILD_TEST_C=1 -DCMAKE_BUILD_TYPE=Release -B ./build_release && cmake --build ./build_release --config RelWithDebInfo",
-            "args": [],
-            "type": "shell",
-            "problemMatcher": [
-                "$msCompile"
-            ],
-            "options": {
-                "shell": {
-                    "executable": "cmd.exe",
-                    "args": [
-                        "/d",
-                        "/c"
-                    ]
-                }
-            }
-        }
-    ]
-}