Skip to content

Commit fec35c3

Browse files
authored
Fix indentation, restore numbering
1 parent b8b3223 commit fec35c3

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

articles/search/semantic-how-to-enable-scoring-profiles.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -48,9 +48,9 @@ In this scenario, a scoring profile is used twice.
4848

4949
1. First, the scoring profile defined in your index is used during the initial L1 ranking phase, boosting results from:
5050

51-
- Text-based queries (BM25 or RRF)
52-
- The text portion of vector queries
53-
- Hybrid queries that combine both types
51+
- Text-based queries (BM25 or RRF)
52+
- The text portion of vector queries
53+
- Hybrid queries that combine both types
5454

5555
1. Next, the semantic ranker rescores the top 50 results, promoting more semantically relevant matches to the top. This step can erase the benefit of the scoring profile. For example, if you boosted based on freshness, then semantic reordering replaces that boost with its own logic of what is most relevant.
5656

0 commit comments

Comments
 (0)