Skip to content

Commit a0b3cb2

Browse files
Merge pull request #2738 from ManoharLakkoju-MSFT/patch-6
(AzureCXP) fixes MicrosoftDocs/azure-ai-docs#363251
2 parents 8d6ff04 + d418e89 commit a0b3cb2

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

articles/search/index-add-scoring-profiles.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -99,7 +99,7 @@ Scoring profiles supplement the default scoring algorithm by boosting the scores
9999

100100
For standalone text queries, scoring profiles identify the maximum 1,000 matches in a [BM25-ranked search](index-similarity-and-scoring.md), and the top 50 are returned in results.
101101

102-
For pure vectors, the query is vector-only, but if the [*k*-matching documents](vector-search-ranking.md) include nonvector fields with human-readable ocntent, a scoring profile can be applied. The scoring profile revises the result set by boosting documents that match criteria in the profile.
102+
For pure vectors, the query is vector-only, but if the [*k*-matching documents](vector-search-ranking.md) include nonvector fields with human-readable content, a scoring profile can be applied. The scoring profile revises the result set by boosting documents that match criteria in the profile.
103103

104104
For text queries in a hybrid query, scoring profiles identify the maximum 1,000 matches in a BM25-ranked search. However, once those 1,000 results are identified, they're restored to their original BM25 order so that they can be rescored alongside vectors results in the final [Reciprocal Ranking Function (RRF)](hybrid-search-ranking.md) ordering, where the scoring profile (identified as "final document boosting adjustment" in the illustration) is applied to the merged results, along with [vector weighting](vector-search-how-to-query.md#vector-weighting), and [semantic ranking](semantic-search-overview.md) as the last step.
105105

0 commit comments

Comments
 (0)