diff --git a/backend/app/modules/data_process/document_chunking.py b/backend/app/modules/data_process/document_chunking.py
index b418e79..2ad97ed 100644
--- a/backend/app/modules/data_process/document_chunking.py
+++ b/backend/app/modules/data_process/document_chunking.py
@@ -90,8 +90,10 @@ def _tokenizer() -> tiktoken.Encoding:
                         token, rank = line.split()
                         mergeable_ranks[base64.b64decode(token)] = int(rank)
 
-                # 构造 Encoding 对象
-                import tiktoken.core
+                # 构造 Encoding 对象（模块顶部已 import tiktoken，
+                # 此处不能再 import tiktoken.core，否则会把 tiktoken
+                # 变成局部变量，使函数开头的 tiktoken.get_encoding 抛
+                # UnboundLocalError）
                 return tiktoken.core.Encoding(
                     name="cl100k_base",
                     pat_str=r"""'(?i:[sdmt]|ll|ve|re)|[^\r\n\p{L}\p{N}]?+\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]++[\r\n]*|\s*[\r\n]|\s+(?!\S)|\s+""",