Update app.py

app.py

@@ -51,6 +51,9 @@ st.set_page_config(layout="wide")
 import logging
 import asyncio
 import re 
+from docx import Document as DocxDocument
+
+
 # Set up logging to suppress Streamlit warnings about experimental functions
 logging.getLogger('streamlit').setLevel(logging.ERROR)
 
@@ -103,25 +106,18 @@ def convert_pdf_to_md(file):
 
 def convert_docx_to_md(file):
     """
-    Convert a .docx file to Markdown text with error handling.
+    Extract text from a .docx file and return as a single string.
     """
     try:
-        file.seek(0)  # Reset file pointer to the beginning
-        doc = Document(file)  # Directly load the file
-
-        markdown_text = ""
-        for paragraph in doc.paragraphs:
-            markdown_text += paragraph.text.strip() + "\n\n"  # Add spacing between paragraphs
-
-        if not markdown_text.strip():
-            st.error("The .docx file is empty or could not be read.")
-            return None
-
-        return markdown_text
-
+        # Read the file
+        doc = DocxDocument(uploaded_file)
+        # Extract all text
+        text = "\n".join([paragraph.text for paragraph in doc.paragraphs])
+        if not text.strip():  # Handle empty content
+            raise ValueError("The document has no content.")
+        return text
     except Exception as e:
-        st.error(f"Error converting .docx file: {e}")
-        return None
+        raise ValueError(f"Error reading .docx file: {e}")
 
 def convert_txt_to_md(file):
     """
@@ -1962,13 +1958,7 @@ def handle_prompt(prompt):
                     # Prevent duplicate messages in chat history
                     if not any(msg["content"] == prompt for msg in st.session_state["chat_history"]):
                         st.session_state.chat_history.append({"role": "user", "content": prompt})
-                    document_response = handle_document_query(prompt)
-                    if document_response:
-                        with st.chat_message("assistant"):
-                            st.markdown(document_response)
-                        st.session_state["handled"] = True  # Mark as handled
-                        return
-
+