fix: 消除 sklearn TfidfVectorizer token_pattern 警告

This commit is contained in:
youpaishidifu
2026-08-05 21:23:22 +08:00
parent 5d9214526b
commit f50eeb28da
+1 -1
View File
@@ -23,7 +23,7 @@ class KnowledgeBase:
def __init__(self, root_path: str = ""):
self.root_path: str = root_path
self.docs: List[dict] = [] # [{path, title, content, heading, section_id}]
self._vectorizer = TfidfVectorizer(tokenizer=self._tokenize, lowercase=False)
self._vectorizer = TfidfVectorizer(tokenizer=self._tokenize, token_pattern=None, lowercase=False)
self._tfidf_matrix = None
self._ready = False
self._heading_token_sets: List[set] = []