Skip to content

Commit f9c83e8

Browse files
authored
Added warning about quantization free service
Free services have limited quota and hence hard to hit the quantization threshold of 10000 documents unless the dimensions is very less. Hence quantization may never happen in SQ
1 parent 61876d6 commit f9c83e8

File tree

1 file changed

+2
-0
lines changed

1 file changed

+2
-0
lines changed

articles/search/vector-search-how-to-quantization.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -42,6 +42,8 @@ Two types of quantization are supported:
4242

4343
- Binary quantization converts floats into binary bits, which takes up 1 bit. This results in up to 28 times reduced vector index size.
4444

45+
**Note:** While free services support quantization, they may not demonstrate the full storage savings due to the limited storage quota.
46+
4547
## Add "compressions" to a search index
4648

4749
The following example shows a partial index definition with a fields collection that includes a vector field, and a `vectorSearch.compressions` section.

0 commit comments

Comments
 (0)