AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-06-04 11:14:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: import jieba.analyse (#12133)

Browse Source 
Signed-off-by: -LAN- <laipz8200@outlook.com>
This commit is contained in:
-LAN- 2024-12-27 11:37:55 +08:00 committed by GitHub
parent 26b5680913
commit dae1b5a619
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
api/core/rag/datasource/keyword/jieba/jieba_keyword_table_handler.py
View File

@ -1,5 +1,5 @@
import re import re
from typing import Optional from typing import Optional, cast
class JiebaKeywordTableHandler: class JiebaKeywordTableHandler:
@ -8,18 +8,20 @@ class JiebaKeywordTableHandler:
from core.rag.datasource.keyword.jieba.stopwords import STOPWORDS from core.rag.datasource.keyword.jieba.stopwords import STOPWORDS
jieba.analyse.default_tfidf.stop_words = STOPWORDS jieba.analyse.default_tfidf.stop_words = STOPWORDS # type: ignore
def extract_keywords(self, text: str, max_keywords_per_chunk: Optional[int] = 10) -> set[str]: def extract_keywords(self, text: str, max_keywords_per_chunk: Optional[int] = 10) -> set[str]:
"""Extract keywords with JIEBA tfidf.""" """Extract keywords with JIEBA tfidf."""
import jieba # type: ignore import jieba.analyse # type: ignore
keywords = jieba.analyse.extract_tags( keywords = jieba.analyse.extract_tags(
sentence=text, sentence=text,
topK=max_keywords_per_chunk, topK=max_keywords_per_chunk,
) )
# jieba.analyse.extract_tags returns list[Any] when withFlag is False by default.
keywords = cast(list[str], keywords)
return set(self._expand_tokens_with_subtokens(keywords)) return set(self._expand_tokens_with_subtokens(set(keywords)))
def _expand_tokens_with_subtokens(self, tokens: set[str]) -> set[str]: def _expand_tokens_with_subtokens(self, tokens: set[str]) -> set[str]:
"""Get subtokens from a list of tokens., filtering for stopwords.""" """Get subtokens from a list of tokens., filtering for stopwords."""