update chinese_text_splitter.py

chains/local_doc_qa.py

@@ -103,7 +103,8 @@ def similarity_search_with_score_by_vector(
                 doc.page_content += doc0.page_content
         if not isinstance(doc, Document):
             raise ValueError(f"Could not find document for id {_id}, got {doc}")
-        docs.append((doc, scores[0][j]))
+        doc_score = min([scores[0][id] for id in [indices[0].tolist().index(i) for i in id_seq if i in indices[0]]])
+        docs.append((doc, doc_score))
     torch_gc()
     return docs
 

configs/model_config.py

@@ -50,6 +50,9 @@ PROMPT_TEMPLATE = """已知信息：
 
 根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
 
+# 文本分句长度
+SENTENCE_SIZE = 100
+
 # 匹配后单段上下文长度
 CHUNK_SIZE = 250
 

textsplitter/chinese_text_splitter.py

 from langchain.text_splitter import CharacterTextSplitter
 import re
 from typing import List
-
+from configs.model_config import SENTENCE_SIZE
 
 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_text1(self, text: str) -> List[str]:
         if self.pdf:
             text = re.sub(r"\n{3,}", "\n", text)
             text = re.sub('\s', ' ', text)
             text = text.replace("\n\n", "")
-        sent_sep_pattern = re.compile('([﹒﹔﹖﹗．。！？]["’”」』]{0,2}|(?=["‘“「『]{1,2}|$))')  # del ：；
+        sent_sep_pattern = re.compile('([﹒﹔；﹖﹗．。！？]["’”」』]{0,2}|(?=["‘“「『]{1,2}|$))')  # del ：；
         sent_list = []
         for ele in sent_sep_pattern.split(text):
             if sent_sep_pattern.match(ele) and sent_list:
@@ -22,4 +22,37 @@ class ChineseTextSplitter(CharacterTextSplitter):
                 sent_list.append(ele)
         return sent_list
 
+    def split_text(self, text: str) -> List[str]:
+        if self.pdf:
+            text = re.sub(r"\n{3,}", r"\n", text)
+            text = re.sub('\s', " ", text)
+            text = re.sub("\n\n", "", text)
+        text = re.sub(r'([;；.!?。！？\?])([^”’])', r"\1\n\2", text)  # 单字符断句符
+        text = re.sub(r'(\.{6})([^"’”」』])', r"\1\n\2", text)  # 英文省略号
+        text = re.sub(r'(\…{2})([^"’”」』])', r"\1\n\2", text)  # 中文省略号
+        text = re.sub(r'([;；!?。！？\?]["’”」』]{0,2})([^;；!?，。！？\?])', r'\1\n\2', text)
+        # 如果双引号前有终止符，那么双引号才是句子的终点，把分句符\n放到双引号后，注意前面的几句都小心保留了双引号
+        text = text.rstrip()  # 段尾如果有多余的\n就去掉它
+        # 很多规则中会考虑分号;，但是这里我把它忽略不计，破折号、英文双引号等同样忽略，需要的再做些简单调整即可。
+        ls = [i for i in text.split("\n") if i]
+        for ele in ls:
+            if len(ele) > SENTENCE_SIZE:
+                ele1 = re.sub(r'([,，.]["’”」』]{0,2})([^,，.])', r'\1\n\2', ele)
+                ele1_ls = ele1.split("\n")
+                for ele_ele1 in ele1_ls:
+                    if len(ele_ele1) > SENTENCE_SIZE:
+                        ele_ele2 = re.sub(r'([\n]{1,}| {2,}["’”」』]{0,2})([^\s])', r'\1\n\2', ele_ele1)
+                        ele2_ls = ele_ele2.split("\n")
+                        for ele_ele2 in ele2_ls:
+                            if len(ele_ele2) > SENTENCE_SIZE:
+                                ele_ele3 = re.sub('( ["’”」』]{0,2})([^ ])', r'\1\n\2', ele_ele2)
+                                ele2_id = ele2_ls.index(ele_ele2)
+                                ele2_ls = ele2_ls[:ele2_id] + [i for i in ele_ele3.split("\n") if i] + ele2_ls[ele2_id + 1:]
+                        ele_id = ele1_ls.index(ele_ele1)
+                        ele1_ls = ele1_ls[:ele_id] + [i for i in ele2_ls if i] + ele1_ls[ele_id + 1:]
+
+                id = ls.index(ele)
+                ls = ls[:id] + [i for i in ele1_ls if i] + ls[id+1:]
+        return ls
+
 

webui.py

@@ -15,8 +15,8 @@ def get_vs_list():
     lst = os.listdir(VS_ROOT_PATH)
     if not lst:
         return lst_default
-    lst.sort(reverse=True)
-    return lst + lst_default
+    lst.sort()
+    return lst_default + lst
 
 
 vs_list = get_vs_list()