Update utils.py

utils.py

@@ -282,7 +282,7 @@ def access_pdf(self, filename):
         return temp_path
 
 #besseren directory Loader als CustomLoader definieren, der den inhalt des dokuemnts, die seitenzahlen, die überschriften und die pfadezu den dokumenten extrahieren
-def create_directory_loader(file_type, directory_path):
+def  create_custom_loader(file_type, file_list): #create_directory_loader(file_type, directory_path):
     loaders = {
         '.pdf': load_pdf_with_metadata,
         '.word': load_word_with_metadata,
@@ -307,9 +307,10 @@ def create_directory_loader(file_type, directory_path):
 
     return CustomLoader(directory_path, file_type, loaders[file_type])
         """
-    def __init__(self, directory_path, file_type, loader_func):
-        self.directory_path = directory_path
+
+    def __init__(self, file_type, file_list, loader_func):
         self.file_type = file_type
+        self.file_list = file_list
         self.loader_func = loader_func
 
     def load(self):
@@ -437,8 +438,11 @@ def document_loading_splitting():
 
     
     # Erstellen von DirectoryLoader für jeden Dateityp
-    pdf_loader = create_directory_loader('.pdf', CHROMA_PDF)
-    word_loader = create_directory_loader('.word', CHROMA_WORD)
+    # pdf_loader = create_directory_loader('.pdf', CHROMA_PDF)
+    #word_loader = create_directory_loader('.word', CHROMA_WORD)
+
+    pdf_loader = create_custom_loader('.pdf', pdf_files)
+    word_loader = create_custom_loader('.docx', word_files)