hnswlib
hnswlib copied to clipboard
nmslib
Header-only C++/python library for fast approximate nearest neighbors
Sorry to bother you again. As you set M larger in level 0 than in other layers, i was wondering the same thing for parameter ef_construction. Whether it is possible...
The commit of apoorv-sharma support multi threads for addPoint? Will this patch reduce the time of the building a hnsw graph?
- mmap support - Accepts pandas Series values without recasting - Support for non-integer labels (labeltype is a template parameter) - Index is stored differently in terms of how element_levels_...
I am using windows. At beginning, I want to run sift test in python, but I cannot download bigann dataset using command line, it shows: 'wget' is not recognized as...
`import numpy as np import hnswlib start = time() num_elements, dim = 500000, 128 INDEX = hnswlib.Index(space="cosine", dim=128) INDEX.init_index(max_elements=num_elements, ef_construction=200, M=16) data = np.loadtxt("./item_vec.txt") item_id = data[:, 0].astype(int) item_vec =...
When I try to build a fresh copy of the library, I encounter the following error: ``` /path/to/hnswlib/tmp$ cmake .. /path/to/hnswlib/tmp$ make Scanning dependencies of target sift_test [ 16%] Building...
Hi, Thanks for making developing this code. Is there a way to get the path the nodes traverse in the hsnw when calling knn_query?
A general question rather than an issue, really --- I've been experimenting with the use of HNSW for a (very slightly) different problem than k-nearest neighbors, and wanted to ask...
```python import hnswlib import numpy as np dim = 128 num_elements = 10000 # Generating sample data data = np.float32(np.random.random((num_elements, dim))) data_labels = np.arange(num_elements) # Declaring index p = hnswlib.Index(space...
what's the difference between sift_1b.cpp and sift_test.cpp?If I want to test with my own data set, which one should I imitate？
