Use patch file to use requests to download dataset for 24.12

context/cuvs-bench/cuvs_bench_get_dataset.patch

@@ -0,0 +1,27 @@
+diff --git a/python/cuvs_bench/cuvs_bench/get_dataset/__main__.py b/python/cuvs_bench/cuvs_bench/get_dataset/__main__.py
+index a6b154ef..b023fcbd 100644
+--- a/python/cuvs_bench/cuvs_bench/get_dataset/__main__.py
++++ b/python/cuvs_bench/cuvs_bench/get_dataset/__main__.py
+@@ -17,7 +17,7 @@ import argparse
+ import os
+ import subprocess
+ import sys
+-from urllib.request import urlretrieve
++import requests
+
+
+ def get_dataset_path(name, ann_bench_data_path):
+@@ -29,7 +29,12 @@ def get_dataset_path(name, ann_bench_data_path):
+ def download_dataset(url, path):
+     if not os.path.exists(path):
+         print(f"downloading {url} -> {path}...")
+-        urlretrieve(url, path)
++        with requests.get(url, stream=True) as r:
++            r.raise_for_status()
++            with open(path, "wb") as f:
++                for chunk in r.iter_content(chunk_size=8192):
++                    if chunk:
++                        f.write(chunk)
+
+
+ def convert_hdf5_to_fbin(path, normalize):

context/cuvs-bench/get_datasets.sh

@@ -3,6 +3,13 @@
 
 set -eo pipefail
 
+# find cuVS in the environment
+PACKAGE_FILE_PATH=$(python -c "import cuvs-bench; print(package_name.__file__)")
+PACKAGE_DIR=$(dirname "$PACKAGE_FILE_PATH")
+
+# Apply the patch
+patch "$PACKAGE_DIR/get_dataset/__main__.py" < cuvs_bench_get_dataset.patch
+
 python -m cuvs_bench.get_dataset --dataset deep-image-96-angular --normalize --dataset-path /home/rapids/preloaded_datasets
 python -m cuvs_bench.get_dataset --dataset fashion-mnist-784-euclidean --dataset-path /home/rapids/preloaded_datasets
 python -m cuvs_bench.get_dataset --dataset glove-50-angular --normalize --dataset-path /home/rapids/preloaded_datasets