upload codes

.clang-format

@@ -0,0 +1,10 @@
+# Defines the Google C++ style for automatic reformatting.
+# http://clang.llvm.org/docs/ClangFormatStyleOptions.html
+BasedOnStyle: Google
+MaxEmptyLinesToKeep: 1
+# ColumnLimit: 0
+FixNamespaceComments: true
+AllowShortFunctionsOnASingleLine: All
+# AlignConsecutiveDeclarations: true
+AlignConsecutiveAssignments: true
+BreakBeforeBraces: Allman

.env

@@ -0,0 +1 @@
+export PATH=$PATH:$HOME/bin:/mnt/pcz/env/cmake-3.24.1-linux-x86_64/bin

.gitignore

@@ -0,0 +1,92 @@
+*.bin
+*.time
+*.png
+*.csv
+
+__pycache__
+*.pyc
+*.so
+*.hdf5
+.DS_Store
+hnswlib.egg-info/
+build/
+dist/
+tmp/
+python_bindings/tests/__pycache__/
+*.pyd
+hnswlib.cpython*.so
+var/
+.idea/
+.vscode/
+
+benchmark/data
+
+benchmark/index
+
+benchmark/latest-results
+
+benchmark/result
+benchmark/results
+
+benchmark/code/gather_statistics.py
+benchmark/code/group1.py
+benchmark/code/group2+3.py
+benchmark/code/group3.py
+benchmark/code/group4.py
+benchmark/code/merge_selectivity.py
+benchmark/code/index.sh
+benchmark/code/plot.py
+benchmark/code/preprocessing_selectivity.py
+benchmark/code/search_ivfpq.py
+
+benchmark/code/search_selectivity.sh
+benchmark/code/search.sh
+benchmark/code/selectivity_test.py
+
+
+
+# Cmake files
+cmake-build-*
+CMakeCache.txt
+CMakeFiles
+CMakeScripts
+Testing
+# Makefile
+cmake_install.cmake
+install_manifest.txt
+compile_commands.json
+CTestTestfile.cmake
+
+# Prerequisites
+*.d
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
+*.exe

ALGO_PARAMS.md

@@ -0,0 +1,31 @@
+# HNSW algorithm parameters
+
+## Search parameters:
+* ```ef``` - the size of the dynamic list for the nearest neighbors (used during the search). Higher ```ef```
+leads to more accurate but slower search. ```ef``` cannot be set lower than the number of queried nearest neighbors
+```k```. The value ```ef``` of can be anything between ```k``` and the size of the dataset.
+* ```k``` number of nearest neighbors to be returned as the result.
+The ```knn_query``` function returns two numpy arrays, containing labels and distances to the k found nearest 
+elements for the queries. Note that in case the algorithm is not be able to find ```k``` neighbors to all of the queries,
+(this can be due to problems with graph or ```k```>size of the dataset) an exception is thrown.
+
+An example of tuning the parameters can be found in [TESTING_RECALL.md](TESTING_RECALL.md)
+
+## Construction parameters:
+* ```M``` - the number of bi-directional links created for every new element during construction. Reasonable range for ```M``` 
+is 2-100. Higher ```M``` work better on datasets with high intrinsic dimensionality and/or high recall, while low ```M``` work 
+better for datasets with low intrinsic dimensionality and/or low recalls. The parameter also determines the algorithm's memory 
+consumption, which is roughly ```M * 8-10``` bytes per stored element.  
+As an example for ```dim```=4 random vectors optimal ```M``` for search is somewhere around 6, while for high dimensional datasets 
+(word embeddings, good face descriptors), higher ```M``` are required (e.g. ```M```=48-64) for optimal performance at high recall. 
+The range ```M```=12-48 is ok for the most of the use cases. When ```M``` is changed one has to update the other parameters. 
+Nonetheless, ef and ef_construction parameters can be roughly estimated by assuming that ```M```*```ef_{construction}``` is 
+a constant.
+
+* ```ef_construction``` - the parameter has the same meaning as ```ef```, but controls the index_time/index_accuracy. Bigger 
+ef_construction leads to longer construction, but better index quality. At some point, increasing ef_construction does
+not improve the quality of the index. One way to check if the selection of ef_construction was ok is to measure a recall 
+for M nearest neighbor search when ```ef``` =```ef_construction```: if the recall is lower than 0.9, than there is room 
+for improvement.
+* ```num_elements``` - defines the maximum number of elements in the index. The index can be extened by saving/loading(load_index
+function has a parameter which defines the new maximum number of elements).

CMakeLists.txt

@@ -0,0 +1,38 @@
+cmake_minimum_required (VERSION 2.8.12)
+project(hnsw_lib LANGUAGES CXX)
+
+set(CMAKE_CXX_STANDARD 17)
+
+# if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+#   SET( CMAKE_CXX_FLAGS  "-Ofast -DNDEBUG -std=c++11 -DHAVE_CXX0X -openmp -fpic -ftree-vectorize")
+#   else()
+#     if (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
+#       SET( CMAKE_CXX_FLAGS  "-Ofast -DNDEBUG -std=c++11 -DHAVE_CXX0X -openmp -march=native -fpic -ftree-vectorize")
+#     elseif (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+#       SET( CMAKE_CXX_FLAGS  "-Ofast -lrt -DNDEBUG -std=c++11 -DHAVE_CXX0X -march=native -fpic -w -fopenmp -ftree-vectorize -ftree-vectorizer-verbose=0" )
+#     elseif (CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
+#       SET( CMAKE_CXX_FLAGS  "-Ofast -lrt -DNDEBUG -std=c++11 -DHAVE_CXX0X -openmp -march=native -fpic -w -fopenmp -ftree-vectorize" )
+#     endif()
+# endif()
+
+# add_executable(test_updates examples/updates_test.cpp)
+# target_link_libraries(test_updates hnswlib)
+
+# add_executable(searchKnnCloserFirst_test examples/searchKnnCloserFirst_test.cpp)
+# target_link_libraries(searchKnnCloserFirst_test hnswlib)
+
+# add_executable(main main.cpp sift_1b.cpp)
+# target_link_libraries(main hnswlib)
+
+# add_subdirectory(googletest)
+
+include_directories(.)
+
+file(GLOB TESTS tests/*.cpp)
+FOREACH (path ${TESTS})
+    get_filename_component(name ${path} NAME_WE)
+    add_executable(${name} ${path})
+ENDFOREACH ()
+
+
+

MANIFEST.in

@@ -0,0 +1,2 @@
+include hnswlib/*.h
+include LICENSE

Makefile

@@ -0,0 +1,15 @@
+pypi: dist
+	twine upload dist/*
+
+dist:
+	-rm dist/*
+	pip install build
+	python3 -m build --sdist
+
+test:
+	python3 -m unittest discover --start-directory python_bindings/tests --pattern "*_test*.py"
+
+clean:
+	rm -rf *.egg-info build dist tmp var tests/__pycache__ hnswlib.cpython*.so
+
+.PHONY: dist