增加语义切分模型 (#248)

textsplitter/chinese_text_splitter.py

 from langchain.text_splitter import CharacterTextSplitter
 import re
 from typing import List
+from modelscope.pipelines import pipeline
 
 
+p = pipeline(
+    task="document-segmentation",
+    model='damo/nlp_bert_document-segmentation_chinese-base',
+    device="cpu")
+
 class ChineseTextSplitter(CharacterTextSplitter):
     def __init__(self, pdf: bool = False, **kwargs):
         super().__init__(**kwargs)
         self.pdf = pdf
 
-    def split_text(self, text: str) -> List[str]:
+    def split_text(self, text: str, use_document_segmentation: bool=False) -> List[str]:
+        # use_document_segmentation参数指定是否用语义切分文档，此处采取的文档语义分割模型为达摩院开源的nlp_bert_document-segmentation_chinese-base，论文见https://arxiv.org/abs/2107.09278
+        # 如果使用模型进行文档语义切分，那么需要安装modelscope[nlp]：pip install "modelscope[nlp]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
+        # 考虑到使用了三个模型，可能对于低配置gpu不太友好，因此这里将模型load进cpu计算，有需要的话可以替换device为自己的显卡id
         if self.pdf:
             text = re.sub(r"\n{3,}", "\n", text)
             text = re.sub('\s', ' ', text)
             text = text.replace("\n\n", "")
+        if use_document_segmentation:
+            result = p(documents=text)
+            sent_list = [i for i in result["text"].split("\n\t") if i]
+        else:
             sent_sep_pattern = re.compile('([﹒﹔﹖﹗．。！？]["’”」』]{0,2}|(?=["‘“「『]{1,2}|$))')  # del ：；
             sent_list = []
             for ele in sent_sep_pattern.split(text):