This library aims at providing useful building blocks to implement algorithms for approximate nearest neighbor search.
This is, first and foremost, a header only library requiring C++17 and depending on cereal and ffht (both libraries are vendored in external).
To integrate with other codebases simply place include/panna in your include path, while making sure that the headers of the dependencies (i.e. the contents of external) are included as well.
That said, the repository includes tests and examples, which are built using cmake with the usual steps
mkdir build
cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make
This produces the following executables:
build/testto run the testsbuild/gloveto run the example onglovebuild/fashionto run the example onfashion-mnist