Examples

This section provides details on how to call the KScaNN algorithm API in Python. In the example, the sift-128-euclidean.hdf5 dataset is used.

Obtaining Test Code

Obtain the test framework code from the source code obtained in 3. Assume that the source code is stored in /path/to/scann/sra_scann_adapter and the test framework code is stored in /path/to/scann/sra_scann_adapter/ann-benchmarks. Obtain datasets.

cd /path/to/scann/sra_scann_adapter/ann-benchmarks
mkdir data && cd data
wget http://ann-benchmarks.com/sift-128-euclidean.hdf5 --no-check-certificate

The directory structure of the main files is as follows:

├── data                                                    // Stores the datasets.
      └── sift-128-euclidean.hdf5
├── ann_benchmarks
      └── algorithms
            └── scann
                  └── config-sift-128-euclidean.yml         // Dataset configuration file.
└── test.sh                                                 // Script for running the test.

Procedure

Check that scann-1.2.10-cp39-cp39-linux_aarch64.whl has been installed in 12.

Install the dependencies required by ann-benchmarks.

cd /path/to/scann/sra_scann_adapter/ann-benchmarks
pip install -r requirements.txt
yum install numactl numactl-devel

Run the test script.
1
sh test.sh
The execution result is as follows:

Parent topic: Python APIs