You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -195,7 +195,7 @@ When compared to FAISS's `IndexFlatL2` in Google Colab, __[USearch may offer up
195
195
196
196
While most vector search packages concentrate on just two metrics, "Inner Product distance" and "Euclidean distance", USearch allows arbitrary user-defined metrics.
197
197
This flexibility allows you to customize your search for various applications, from computing geospatial coordinates with the rare [Haversine][haversine] distance to creating custom metrics for composite embeddings from multiple AI models, like joint image-text embeddings.
198
-
You can use [Numba][numba], [Cppyy][cppyy], or [PeachPy][peachpy] to define your [custom metric even in Python](https://unum-cloud.github.io/usearch/python#user-defined-metrics-and-jit-in-python):
198
+
You can use [Numba][numba], [Cppyy][cppyy], or [PeachPy][peachpy] to define your [custom metric even in Python](https://unum-cloud.github.io/USearch/python#user-defined-metrics-and-jit-in-python):
199
199
200
200
```py
201
201
from numba import cfunc, types, carray
@@ -552,7 +552,7 @@ doi = {10.5281/zenodo.7949416},
0 commit comments