Ai data mask deny word match optimize (#1453)

This commit is contained in:
007gzs
2024-11-05 15:26:55 +08:00
committed by GitHub
parent 7e8b0445ad
commit c1f2504e87
7 changed files with 78 additions and 50 deletions

View File

@@ -129,3 +129,4 @@ Please note that you need to replace `"key":"value"` with the actual data conten
- In streaming mode, if sensitive words are split across multiple chunks, there may be cases where part of the sensitive word is returned to the user
- Grok built-in rule list: https://help.aliyun.com/zh/sls/user-guide/grok-patterns
- Built-in sensitive word library data source: https://github.com/houbb/sensitive-word/tree/master/src/main/resources
- Since the sensitive word list is matched after tokenizing the text, please set `deny_words` to single words. In the case of multiple words in English, such as `hello world`, the match may not be successful.