hnswlib
hnswlib copied to clipboard
Header-only C++/python library for fast approximate nearest neighbors
This logic ranks the squared differences between the query vector parameters and the learned vector parameters used in Euclidean distance calculations. If this logic is customized and added to the...
hello: When the data volume is large, such as 900 million documents, an exception is thrown by loadIndex, as shown in the figure below. What is the cause of this...
Is there any transformation for webAssembly or any known project?
Hi, I am trying to use this and can't even get the simplest of example code to work. I have a python environment created with conda ``` conda create -n...
hello: When testing recall rate using the bindings_test_recall.py script, I found that the recall rate drops significantly after normalizing the vectors. The metrics used are inner product. In this case,...
Hello, After I download the released zip files 0.8, I got an error when I try to unzip it.  Should I just ignore it? Or maybe something is wrong?
``` exclude: - os: macos-latest python-version: "3.7" ```
I want to load network resourse to index but it failed ```python import requests import io import pickle import hnswlib def get_stream(url): response = requests.get(url) stream_data = response.content return io.BytesIO(stream_data)...
Hi, folks. I found the problem on hnswlib 0.8.0 as follows: ``` root@ip-mask:/app# python --version Python 3.11.2 root@ip-mask:/app# uname -a Linux ip-mask.ap-northeast-1.compute.internal 4.14.343-261.564.amzn2.aarch64 #1 SMP Tue May 7 02:23:29 UTC...
Hello, I am creating various indexes with the following options: * space: l2 * vector dimension: 256 * M: 16 * ef_construction: 200 * ef: 200 The number of items...