Update app.py

app.py

@@ -17,38 +17,7 @@ def load_model():
 
  
     return model
-###################################################
 
-
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-
-class QQQSplitter(RecursiveCharacterTextSplitter):
-    def __init__(self):
-        super().__init__()
-
-    def split(self, text: str) -> List[str]:
-        """
-        Splits the given text whenever there is a "qqq" sequence.
-        """
-        parts = []
-        current_part = ""
-
-        for char in text:
-            if char == "q":
-                if len(current_part) > 0 and current_part[-1] == "q":
-                    # Found a "qqq" sequence, split!
-                    parts.append(current_part[:-1])
-                    current_part = ""
-                else:
-                    current_part += char
-            else:
-                current_part += char
-
-        parts.append(current_part)
-        return parts
-
-
-    ######################################
 ##################################################
 ## vs chat
 ##################################################
@@ -117,7 +86,7 @@ def load_txt(path="./a.cv.ckaller.2024.txt"):
 #####
 
 
-    text_splitter = QQQSplitter(HuggingFaceBgeEmbeddings())
+    text_splitter = SemanticChunker(HuggingFaceBgeEmbeddings())
      
     document_chunks = text_splitter.create_documents([state_of_the_union])
     print(document_chunks[0].page_content)