From b022615b2cfb9ca224d02ffdc0b484f0f0c58513 Mon Sep 17 00:00:00 2001 From: Xieql Date: Mon, 27 Dec 2021 10:24:17 +0800 Subject: [PATCH] [skip e2e] improve annotation (#14127) Signed-off-by: Xieql --- .../index/thirdparty/faiss/benchs/distributed_ondisk/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/internal/core/src/index/thirdparty/faiss/benchs/distributed_ondisk/README.md b/internal/core/src/index/thirdparty/faiss/benchs/distributed_ondisk/README.md index 5ee33d1f1f..aa150334e4 100644 --- a/internal/core/src/index/thirdparty/faiss/benchs/distributed_ondisk/README.md +++ b/internal/core/src/index/thirdparty/faiss/benchs/distributed_ondisk/README.md @@ -125,7 +125,7 @@ This is performed by the script [`make_trained_index.py`](make_trained_index.py) ## Building the index by slices -We call the slices "vslisces" as they are vertical slices of the big matrix, see explanation in the wiki section [Split across datanbase partitions](https://github.com/facebookresearch/faiss/wiki/Indexing-1T-vectors#split-across-database-partitions). +We call the slices "vslisces" as they are vertical slices of the big matrix, see explanation in the wiki section [Split across database partitions](https://github.com/facebookresearch/faiss/wiki/Indexing-1T-vectors#split-across-database-partitions). The script [make_index_vslice.py](make_index_vslice.py) makes an index for a subset of the vectors of the input data and stores it as an independent index. There are 200 slices of 5M vectors each for Deep1B.