update import pkgs and format

text_splitter/__init__.py

@@ -1,3 +1,3 @@
 from .chinese_text_splitter import ChineseTextSplitter
 from .ali_text_splitter import AliTextSplitter
-from .zh_title_enhance import zh_title_enhance
+from .zh_title_enhance import zh_title_enhance

text_splitter/ali_text_splitter.py

@@ -16,7 +16,14 @@ class AliTextSplitter(CharacterTextSplitter):
             text = re.sub(r"\n{3,}", r"\n", text)
             text = re.sub('\s', " ", text)
             text = re.sub("\n\n", "", text)
-        from modelscope.pipelines import pipeline
+        try:
+            from modelscope.pipelines import pipeline
+        except ImportError:
+            raise ImportError(
+                "Could not import modelscope python package. "
+                "Please install modelscope with `pip install modelscope`. "
+            )
+
 
         p = pipeline(
             task="document-segmentation",

text_splitter/chinese_text_splitter.py

@@ -1,11 +1,11 @@
 from langchain.text_splitter import CharacterTextSplitter
 import re
 from typing import List
-from configs.model_config import SENTENCE_SIZE
+from configs.model_config import CHUNK_SIZE
 
 
 class ChineseTextSplitter(CharacterTextSplitter):
-    def __init__(self, pdf: bool = False, sentence_size: int = SENTENCE_SIZE, **kwargs):
+    def __init__(self, pdf: bool = False, sentence_size: int = CHUNK_SIZE, **kwargs):
         super().__init__(**kwargs)
         self.pdf = pdf
         self.sentence_size = sentence_size