From 994d1665cb61d15a7f3d44d03fc489227ee84bbc Mon Sep 17 00:00:00 2001 From: Leonid Boytsov Date: Thu, 8 Feb 2018 00:41:32 -0500 Subject: [PATCH] Update README.md --- python_bindings/notebooks/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python_bindings/notebooks/README.md b/python_bindings/notebooks/README.md index b97f414..593a789 100644 --- a/python_bindings/notebooks/README.md +++ b/python_bindings/notebooks/README.md @@ -1,4 +1,4 @@ -We have three Notebooks: two are for dense spaces and one is for the sparse space. For the dense space, we have examples of the so-called optimized and non-optimized indices. Except HNSW, all the methods save meta-indices rather than real onese. Meta indices contain only index structure, but not the data. Hence, before a meta-index can be loaded, we need to re-load data. +We have three Notebooks: three are for dense spaces and one is for the sparse space. For the dense space, we have examples of the so-called optimized and non-optimized indices. Except HNSW, all the methods save meta-indices rather than real onese. Meta indices contain only index structure, but not the data. Hence, before a meta-index can be loaded, we need to re-load data. One example is a memory efficient space to search for SIFT vectors. HNSW, can save real indices, but only for the dense spaces: Euclidean and the cosine. When you use these optimized indices, the search does not require reloading all the data. However, reloading the data is **required** if you want to use the function **getDistance**. Furthermore, creation of the optimized index can always be disabled specifying the index-time parameter **skip_optimized_index** (value 1).