New run March 2025

README.md

@@ -78,7 +78,7 @@ We have a number of precomputed data sets in HDF5 format. All data sets have bee
 Results
 =======
 
-These are all as of April 2023, running all benchmarks on a r6i.16xlarge machine on AWS with `--parallelism 31` and hyperthreading disabled. All benchmarks are single-CPU.
+These are all as of April 2025, running all benchmarks on a r6i.16xlarge machine on AWS with `--parallelism 31` and hyperthreading disabled. All benchmarks are single-CPU.
 
 glove-100-angular
 -----------------
@@ -124,9 +124,9 @@ The only prerequisite is Python (tested with 3.10.6) and Docker.
 Running
 =======
 
-1. Run `python run.py` (this can take an extremely long time, potentially days)
-2. Run `python plot.py` or `python create_website.py` to plot results.
-3. Run `python data_export.py --out res.csv` to export all results into a csv file for additional post-processing.
+1. Run `python run.py` (this can take an extremely long time, potentially days).
+2. Run `python plot.py --x-scale logit --y-scale log` to plot results.
+3. Run `python create_website.py` to create a website with lots of plots.
 
 You can customize the algorithms and datasets as follows:
 

ann_benchmarks/algorithms/base/Dockerfile

@@ -1,12 +1,11 @@
 FROM ubuntu:22.04
 
 RUN apt-get update
-RUN apt-get install -y python3-numpy python3-scipy python3-pip build-essential git
-RUN pip3 install -U pip
-RUN python3 --version | grep 'Python 3.10'
+RUN apt-get install -y python3-pip python-is-python3 build-essential git
+RUN python --version | grep 'Python 3.10'
 
 WORKDIR /home/app
 COPY requirements.txt run_algorithm.py ./
-RUN pip3 install -r requirements.txt
+RUN pip install -r requirements.txt
 
-ENTRYPOINT ["python3", "-u", "run_algorithm.py"]
+ENTRYPOINT ["python", "-u", "run_algorithm.py"]

ann_benchmarks/algorithms/hnswlib/Dockerfile

@@ -1,10 +1,9 @@
 FROM ann-benchmarks
 
-RUN apt-get install -y python-setuptools python-pip
-RUN pip3 install pybind11 numpy setuptools
-RUN git clone https://github.com/nmslib/hnsw.git;cd hnsw; git checkout denorm
+RUN pip install pybind11 numpy setuptools
+RUN git clone https://github.com/nmslib/hnsw.git; cd hnsw; git checkout denorm
 
 RUN cd hnsw/python_bindings; python3 setup.py install
 
-RUN python3 -c 'import hnswlib'
+RUN python -c 'import hnswlib'
 

ann_benchmarks/algorithms/kgraph/Dockerfile

@@ -1,6 +1,6 @@
 FROM ann-benchmarks
 
-RUN apt-get update && apt-get install -y libboost-timer-dev libboost-chrono-dev libboost-program-options-dev libboost-system-dev libboost-python-dev
+RUN apt-get update && apt-get install -y libboost-timer-dev libboost-chrono-dev libboost-program-options-dev libboost-system-dev libboost-python-dev libopenblas-dev
 RUN git clone https://github.com/aaalgo/kgraph
-RUN cd kgraph && python3 setup.py build && python3 setup.py install
-RUN python3 -c 'import pykgraph'
+RUN cd kgraph && pip install -e .
+RUN python -c 'import kgraph'

ann_benchmarks/algorithms/kgraph/module.py

@@ -1,7 +1,7 @@
 import os
 
 import numpy
-import pykgraph
+import kgraph
 
 from ...constants import INDEX_DIR
 from ..base.module import BaseANN
@@ -18,7 +18,7 @@ def __init__(self, metric, index_params, save_index):
     def fit(self, X):
         if X.dtype != numpy.float32:
             X = X.astype(numpy.float32)
-        self._kgraph = pykgraph.KGraph(X, self._metric)
+        self._kgraph = kgraph.KGraph(X, self._metric)
         path = os.path.join(INDEX_DIR, "kgraph-index-%s" % self._metric)
         if os.path.exists(path):
             self._kgraph.load(path)

ann_benchmarks/algorithms/nearpy/Dockerfile

@@ -1,5 +1,5 @@
 FROM ann-benchmarks
 
-RUN apt-get install -y libhdf5-openmpi-dev cython
-RUN pip3 install nearpy bitarray redis sklearn
-RUN python3 -c 'import nearpy'
+RUN apt-get install -y libhdf5-openmpi-dev cython3
+RUN pip install nearpy bitarray redis
+RUN python -c 'import nearpy'

ann_benchmarks/algorithms/puffinn/Dockerfile

@@ -1,6 +1,6 @@
 FROM ann-benchmarks
 
-RUN pip3 install pypandoc==1.4
+RUN pip install pypandoc==1.4 pybind11
 RUN git clone https://github.com/puffinn/puffinn
-RUN cd puffinn && python3 setup.py install
-RUN python3 -c 'import puffinn'
+RUN cd puffinn && python setup.py install
+RUN python -c 'import puffinn'

ann_benchmarks/algorithms/vearch/Dockerfile

@@ -1,4 +1,5 @@
 FROM ann-benchmarks
 
-RUN pip3 install vearch==3.2.8.3
-RUN python3 -c 'import vearch'
+RUN pip install 'numpy<2'
+RUN pip install vearch==3.2.8.3
+RUN python -c 'import vearch'

ann_benchmarks/algorithms/voyager/Dockerfile

@@ -1,7 +1,7 @@
 FROM ann-benchmarks
 
-RUN apt-get install -y python-setuptools python-pip
-RUN pip3 install voyager
+RUN apt-get install -y python-setuptools
+RUN pip install voyager
 
-RUN python3 -c 'import voyager'
+RUN python -c 'import voyager'
 

plot.py

@@ -88,7 +88,7 @@ def inv_fun(x):
     # Workaround for bug https://github.com/matplotlib/matplotlib/issues/6789
     ax.spines["bottom"]._adjust_location()
 
-    plt.savefig(fn_out, bbox_inches="tight")
+    plt.savefig(fn_out, bbox_inches="tight", dpi=144)
     plt.close()
 
 
@@ -108,7 +108,7 @@ def inv_fun(x):
         "-y", "--y-axis", help="Which metric to use on the Y-axis", choices=metrics.keys(), default="qps"
     )
     parser.add_argument(
-        "-X", "--x-scale", help="Scale to use when drawing the X-axis. Typically linear, logit or a2", default="linear"
+        "-X", "--x-scale", help="Scale to use when drawing the X-axis. Typically linear, logit or a2", default="linear",
     )
     parser.add_argument(
         "-Y",

requirements.txt

@@ -1,12 +1,12 @@
 ansicolors==1.1.8
 docker==7.1.0
-h5py==3.8.0
-matplotlib==3.6.3
-numpy==1.24.2
-pyyaml==6.0
-psutil==5.9.4
-scikit-learn==1.2.1
-jinja2==3.1.2
-pytest==7.2.2
-datasets==2.12.0
-requests==2.31.0
+h5py==3.13.0
+matplotlib==3.10.1
+numpy==2.2.4
+pyyaml==6.0.2
+psutil==7.0.0
+scikit-learn==1.6.1
+jinja2==3.1.6
+pytest==8.3.5
+datasets==3.4.0
+requests==2.32.3