ann-benchmarks
ann-benchmarks copied to clipboard
erikbern
Benchmarks of approximate nearest neighbor libraries in Python
I run the benchmark on Ubuntu 23.04 with Docker for pgvector algorithm only. The docker image was built without any problem. However, when I try to execute `python run.py --algorithm...
Hi , I am testing vespa which is running in cloud , Can you share where i can pass the cluster connection details.
This commit inspired by timescale blog post publication [1] about performance improvements over current implementation of the pgvector [2] implementation. Adding a benchmark to evaluate implementation suggested by PgVectorScale project....
I’m trying to understand the variability in the Test Size of the datasets provided and if that has an impact on the QPS. The test sizes for [datasets](https://github.com/erikbern/ann-benchmarks?tab=readme-ov-file#data-sets) listed vary...
# Question Can I use the "_ground truth_" part of angular datasets for inner product, after normalizing the "_data_" part. If not, are there any datasets for inner product? I...
We found that faiss container uses conda/mkl and couldnt force it to use AOCL. We also found that on faiss standalone app compiled from sources and usses AOCL's libblis-mt ,...
MariaDB supports Vector now. https://mariadb.com/kb/en/vector-overview/ Add new module for benchmark against MariaDB 11.8 database server.
Hi! Team: I've been trying to test several algorithms on the benchmark and used the following command: `python3 run.py --parallelism 31 --dataset gist-960-euclidean --runs 5 --force` I found that many...
Hey @erikbern and ANN Benchmarking team!, Thanks for adding this clean implementation. i have two query - 1) not a easy way to run test with custom data, i have...
