Update app.py

app.py

@@ -85,11 +85,21 @@ class StreamlitDocProcessor:
         st.title("Document Assistant")
         
         # Create sidebar for navigation
+        st.sidebar.title("Navigation")
         page = st.sidebar.selectbox(
             "Choose a page",
             ["Upload & Process", "Query"]
         )
         
+        # Add sidebar information
+        with st.sidebar.expander("About"):
+            st.write("""
+            This application allows you to:
+            - Upload PDF and XML documents
+            - Process them for semantic search
+            - Query the documents with different levels of detail
+            """)
+            
         if page == "Upload & Process":
             self.upload_and_process_page()
         else:
@@ -98,18 +108,32 @@ class StreamlitDocProcessor:
     def upload_and_process_page(self):
         st.header("Upload and Process Documents")
         
+        # Add instructions
+        with st.expander("Instructions", expanded=True):
+            st.write("""
+            1. Click 'Browse files' to select documents
+            2. You can select multiple files at once
+            3. Supported formats: PDF and XML
+            4. Wait for processing to complete
+            5. Processed files will be listed below
+            """)
+        
         # File uploader
         uploaded_files = st.file_uploader(
             "Upload PDF or XML files",
             type=['pdf', 'xml'],
-            accept_multiple_files=True
+            accept_multiple_files=True,
+            help="Select one or more PDF or XML files to upload"
         )
 
         if uploaded_files:
             for uploaded_file in uploaded_files:
-                # Create progress bar
-                progress_bar = st.progress(0)
-                status_text = st.empty()
+                # Create progress bar and status container
+                col1, col2 = st.columns([3, 1])
+                with col1:
+                    progress_bar = st.progress(0)
+                with col2:
+                    status_text = st.empty()
                 
                 # Check if file is already processed
                 file_ext = os.path.splitext(uploaded_file.name)[1][1:]  # Get extension without dot
@@ -121,7 +145,7 @@ class StreamlitDocProcessor:
                             temp_path = tmp_file.name
 
                         # Process the file
-                        status_text.text(f'Processing {uploaded_file.name}...')
+                        status_text.info('Processing...')
                         progress_bar.progress(25)
                         
                         result = st.session_state.processor.process_file(temp_path)
@@ -132,13 +156,15 @@ class StreamlitDocProcessor:
                                 st.session_state.processed_files[file_ext] = []
                             st.session_state.processed_files[file_ext].append(uploaded_file.name)
                             progress_bar.progress(100)
-                            status_text.success(f"Successfully processed {uploaded_file.name}")
+                            status_text.success("✓ Success")
                         else:
                             progress_bar.progress(100)
-                            status_text.error(f"Failed to process {uploaded_file.name}: {result['error']}")
+                            status_text.error("✗ Failed")
+                            st.error(f"Failed to process {uploaded_file.name}: {result['error']}")
 
                     except Exception as e:
-                        status_text.error(f"Error processing {uploaded_file.name}: {str(e)}")
+                        status_text.error("✗ Error")
+                        st.error(f"Error processing {uploaded_file.name}: {str(e)}")
                     finally:
                         # Clean up temporary file
                         try:
@@ -146,26 +172,30 @@ class StreamlitDocProcessor:
                         except:
                             pass
                 else:
-                    status_text.info(f"{uploaded_file.name} has already been processed")
+                    status_text.info("Already processed")
                     progress_bar.progress(100)
 
         # Display processed files
         if any(st.session_state.processed_files.values()):
             st.subheader("Processed Files")
-            if st.session_state.processed_files.get('xml'):
-                st.write("XML Files:")
-                for file in sorted(st.session_state.processed_files['xml']):
-                    st.text(f"📱 {file}")
-            if st.session_state.processed_files.get('pdf'):
-                st.write("PDF Files:")
-                for file in sorted(st.session_state.processed_files['pdf']):
-                    st.text(f"📄 {file}")
-
-    # Modify the qa_page method in the StreamlitDocProcessor class
+            
+            col1, col2 = st.columns(2)
+            
+            with col1:
+                if st.session_state.processed_files.get('xml'):
+                    st.write("📱 XML Files:")
+                    for file in sorted(st.session_state.processed_files['xml']):
+                        st.text(f"  • {file}")
+                        
+            with col2:
+                if st.session_state.processed_files.get('pdf'):
+                    st.write("📄 PDF Files:")
+                    for file in sorted(st.session_state.processed_files['pdf']):
+                        st.text(f"  • {file}")
 
     def qa_page(self):
         st.header("Query Documents")
-    
+
         try:
             # Refresh available files
             st.session_state.processed_files = self.get_processed_files()
@@ -173,105 +203,126 @@ class StreamlitDocProcessor:
             if not any(st.session_state.processed_files.values()):
                 st.warning("No processed files available. Please upload and process some files first.")
                 return
-    
+
             # Create combined list of files with icons
             all_files = []
             for file in st.session_state.processed_files.get('xml', []):
                 all_files.append(f"📱 {file}")
             for file in st.session_state.processed_files.get('pdf', []):
                 all_files.append(f"📄 {file}")
-    
+
             if not all_files:
                 st.warning("No processed files available. Please upload and process some files first.")
                 return
-    
+
+            # Add query instructions
+            with st.expander("Query Instructions", expanded=True):
+                st.write("""
+                Choose your query type:
+                - **Quick Answer**: Basic response with essential information
+                - **Detailed Answer**: Shows sources and relevance with expandable details
+                - **Complete Analysis**: Provides summary and full breakdown with XML hierarchies
+                """)
+
             # File selection
             selected_files = st.multiselect(
                 "Select files to search through",
                 sorted(all_files),
-                default=all_files
+                default=all_files,
+                help="Choose which files to include in your search"
             )
-    
+
             # Remove icons from selected files
             selected_files = [f.split(' ', 1)[1] for f in selected_files]
-    
+
             if not selected_files:
                 st.warning("Please select at least one file to search through.")
                 return
 
-        # Question input
-        question = st.text_input("Enter your question:")
-        
-        if question:
-            col1, col2, col3 = st.columns(3)
+            # Question input
+            question = st.text_input(
+                "Enter your question:",
+                help="Type your question here and choose a query type below"
+            )
             
-            with col1:
-                if st.button("Quick Answer"):
-                    try:
-                        with st.spinner("Getting quick answer..."):
-                            answer = st.session_state.processor.ask_question_selective(
-                                question,
-                                selected_files
-                            )
-                            st.write("Answer:", answer)
-                    except Exception as e:
-                        st.error(f"Error getting answer: {str(e)}")
+            if question:
+                col1, col2, col3 = st.columns(3)
+                
+                with col1:
+                    if st.button("Quick Answer", help="Get a concise answer quickly"):
+                        try:
+                            with st.spinner("Getting quick answer..."):
+                                answer = st.session_state.processor.ask_question_selective(
+                                    question,
+                                    selected_files
+                                )
+                                st.write("Answer:", answer)
+                        except Exception as e:
+                            st.error(f"Error getting answer: {str(e)}")
 
-            with col2:
-                if st.button("Detailed Answer"):
-                    try:
-                        with st.spinner("Getting detailed answer..."):
-                            result = st.session_state.processor.get_detailed_context(
-                                question,
-                                selected_files
-                            )
-                            if result['success']:
-                                st.write("### Relevant Information")
-                                for item in result['results']:
-                                    with st.expander(f"Source: {item['metadata']['source_file']} ({item['metadata']['content_type'].upper()})"):
-                                        st.write(f"Relevance Score: {item['relevance_score']:.2f}")
-                                        if item['metadata']['content_type'] == 'xml':
-                                            st.write(f"XML Path: {item['source_info']['path']}")
-                                        st.write("Content:", item['content'])
-                            else:
-                                st.error(result['error'])
-                    except Exception as e:
-                        st.error(f"Error getting detailed answer: {str(e)}")
+                with col2:
+                    if st.button("Detailed Answer", help="Get answer with sources and relevance scores"):
+                        try:
+                            with st.spinner("Getting detailed answer..."):
+                                result = st.session_state.processor.get_detailed_context(
+                                    question,
+                                    selected_files
+                                )
+                                if result['success']:
+                                    st.write("### Relevant Information")
+                                    for item in result['results']:
+                                        with st.expander(f"Source: {item['metadata']['source_file']} ({item['metadata']['content_type'].upper()})"):
+                                            st.write(f"Relevance Score: {item['relevance_score']:.2f}")
+                                            if item['metadata']['content_type'] == 'xml':
+                                                st.write(f"XML Path: {item['source_info']['path']}")
+                                            st.write("Content:", item['content'])
+                                else:
+                                    st.error(result['error'])
+                        except Exception as e:
+                            st.error(f"Error getting detailed answer: {str(e)}")
 
-            with col3:
-                if st.button("Complete Analysis"):
-                    try:
-                        with st.spinner("Performing complete analysis..."):
-                            result = st.session_state.processor.get_summary_and_details(
-                                question,
-                                selected_files
-                            )
-                            if result['success']:
-                                st.write("### Summary")
-                                st.write(result['summary'])
-                                
-                                st.write("### Detailed Information")
-                                for item in result['details']:
-                                    with st.expander(f"Source: {item['metadata']['source_file']} ({item['metadata']['content_type'].upper()})"):
-                                        st.write(f"Relevance Score: {item['relevance_score']:.2f}")
-                                        if item['metadata']['content_type'] == 'xml':
-                                            st.write(f"XML Path: {item['source_info']['path']}")
-                                            if 'parent_info' in item:
-                                                st.write("Parent Element:", item['parent_info']['content'])
-                                            if 'children_info' in item:
-                                                st.write("Related Elements:")
-                                                for child in item['children_info']:
-                                                    st.write(f"- {child['content']}")
-                                        st.write("Content:", item['content'])
-                            else:
-                                st.error(result['error'])
-                    except Exception as e:
-                        st.error(f"Error getting complete analysis: {str(e)}")
+                with col3:
+                    if st.button("Complete Analysis", help="Get comprehensive analysis with XML hierarchy"):
+                        try:
+                            with st.spinner("Performing complete analysis..."):
+                                result = st.session_state.processor.get_summary_and_details(
+                                    question,
+                                    selected_files
+                                )
+                                if result['success']:
+                                    st.write("### Summary")
+                                    st.write(result['summary'])
+                                    
+                                    st.write("### Detailed Information")
+                                    for item in result['details']:
+                                        with st.expander(f"Source: {item['metadata']['source_file']} ({item['metadata']['content_type'].upper()})"):
+                                            st.write(f"Relevance Score: {item['relevance_score']:.2f}")
+                                            if item['metadata']['content_type'] == 'xml':
+                                                st.write(f"XML Path: {item['source_info']['path']}")
+                                                if 'parent_info' in item:
+                                                    st.write("Parent Element:", item['parent_info']['content'])
+                                                if 'children_info' in item:
+                                                    st.write("Related Elements:")
+                                                    for child in item['children_info']:
+                                                        st.write(f"- {child['content']}")
+                                            st.write("Content:", item['content'])
+                                else:
+                                    st.error(result['error'])
+                        except Exception as e:
+                            st.error(f"Error getting complete analysis: {str(e)}")
                     
         except Exception as e:
             st.error(f"Error in Q&A interface: {str(e)}")
 
 def main():
+    # Set page config
+    st.set_page_config(
+        page_title="Document Assistant",
+        page_icon="📚",
+        layout="wide",
+        initial_sidebar_state="expanded"
+    )
+    
     # Initialize session state
     initialize_session_state()