Update utils.py

utils.py

@@ -244,6 +244,31 @@ def create_directory_loader(file_type, directory_path):
 ################################################
 # Custom Loader-Funktionen zu dem DirektoryLoader
 # Custom loader functions
+def load_pdf_with_metadata(file_path):
+    document = fitz.open(file_path)
+    documents = []
+    for page_num in range(len(document)):
+        page = document.load_page(page_num)
+        content = page.get_text("text")
+        title = document.metadata.get("title", "Unbekannt")
+        page_number = page_num + 1
+        documents.append(Document(content=content, title=title, page=page_number, path=file_path))
+    return documents
+
+def load_word_with_metadata(file_path):
+    document = docx.Document(file_path)
+    title = "Dokument"
+    path = file_path
+    documents = []
+    for para in document.paragraphs:
+        content = para.text
+        page_number = 1  # Word-Dokumente haben keine Seitenzahlen in diesem Kontext
+        documents.append(Document(content=content, title=title, page=page_number, path=path))
+    return documents
+
+
+"""
+# Custom loader functions
 def load_pdf_with_metadata(file_path):
     document = fitz.open(file_path)
     documents = []
@@ -269,7 +294,7 @@ def load_word_with_metadata(file_path):
         content = para.text
         contents.append({"page_content": content, "metadata": {**metadata, "page": 1}})
     return contents
-
+"""
     
     
 ################################################