Update src/app.py

src/app.py

@@ -10,7 +10,7 @@ from pathlib import Path
 # Import optimized versions
 from pdf_parser import PDFParser
 from vector_store import VectorStore
-from rag_system import VisualMultimodalRAG  # NEW - Vision model
+from rag_system import VisualMultimodalRAG, AnsweringRAG  # NEW - Vision model
 from config import UPLOAD_FOLDER, MAX_PDF_SIZE_MB
 
 
@@ -59,6 +59,9 @@ if 'current_tables' not in st.session_state:
 if 'processing_results' not in st.session_state:  # NEW
     st.session_state.processing_results = None
 
+if 'answering_rag' not in st.session_state:
+    st.session_state.answering_rag = None
+
 
 # ============================================================================
 # MAIN HEADER
@@ -317,13 +320,22 @@ if st.button("🖼️ Analyze Images Visually & Store Components"):
 st.divider()
 st.header("❓ Ask Questions About Document")
 
+# Initialize answering system if not done
+if 'answering_rag' not in st.session_state:
+    st.session_state.answering_rag = None
+
+# Create answering system when API key is set
+if st.session_state.api_key_set and st.session_state.answering_rag is None:
+    from rag_system_answering import AnsweringRAG
+    st.session_state.answering_rag = AnsweringRAG(api_key=st.session_state.api_key, debug=True)
+
 question = st.text_area(
     "Enter your question:",
     height=100,
     placeholder="What does the document say about...?"
 )
 
-if st.button("🔍 Search & Answer"):
+if st.button("🔍 Search & Generate Answer"):
     if not st.session_state.api_key_set:
         st.error("❌ Please set OpenAI API key first")
     elif st.session_state.current_text is None:
@@ -332,7 +344,7 @@ if st.button("🔍 Search & Answer"):
         st.error("❌ Please enter a question")
     else:
         try:
-            with st.spinner("🔄 Searching and generating answer..."):
+            with st.spinner("🔄 Searching document and analyzing..."):
                 print(f"\n{'='*70}")
                 print(f"QUESTION: {question}")
                 print(f"{'='*70}")
@@ -340,32 +352,61 @@ if st.button("🔍 Search & Answer"):
                 # Search vector store
                 store = st.session_state.vector_store
                 
-                # Add documents to store first if not already added
+                # Add documents to store if needed
                 doc_name = st.session_state.current_document or "current_doc"
                 doc_data = {
                     'text': st.session_state.current_text,
-                    'images': [],  # Images already stored via visual analysis
-                    'tables': []   # Tables already stored via visual analysis
+                    'images': [],
+                    'tables': []
                 }
                 store.add_documents(doc_data, doc_name)
                 
-                # Search
+                # Search for relevant results
                 search_results = store.search(question, n_results=5)
                 
-                # Display results
-                st.write("### Search Results")
-                for idx, result in enumerate(search_results, 1):
-                    content_type = result.get('type', 'unknown')
-                    distance = result.get('distance', 0)
-                    content = result.get('content', '')
-                    
-                    with st.expander(
-                        f"Result {idx} - {content_type.upper()} "
-                        f"(relevance: {1-distance:.2%})"
-                    ):
-                        st.write(content)
+                print(f"\n📊 Search Results Found: {len(search_results)}")
+                
+                # Analyze results and generate answer
+                answering_rag = st.session_state.answering_rag
+                result = answering_rag.analyze_and_answer(question, search_results)
+                
+                # Display answer prominently
+                st.success("✅ Analysis complete!")
+                
+                st.subheader("📝 Answer")
+                
+                # Show confidence level
+                col1, col2, col3 = st.columns(3)
+                with col1:
+                    confidence_color = {
+                        'high': '🟢',
+                        'medium': '🟡',
+                        'low': '🔴'
+                    }.get(result['confidence'], '⚪')
+                    st.metric("Confidence", f"{confidence_color} {result['confidence'].upper()}")
+                with col2:
+                    st.metric("Sources Used", result['sources_used'])
+                with col3:
+                    if result['sources_used'] > 0:
+                        st.metric("Avg Relevance", f"{sum(1-r.get('distance',0) for r in search_results)/len(search_results):.0%}")
+                
+                # Display the generated answer
+                st.write(result['answer'])
+                
+                # Show sources
+                if st.checkbox("📚 Show Source Documents"):
+                    st.subheader("Sources Used in Answer")
+                    for idx, source in enumerate(result['formatted_sources'], 1):
+                        relevance = source['relevance']
+                        relevance_bar = "█" * int(relevance * 10) + "░" * (10 - int(relevance * 10))
+                        
+                        with st.expander(
+                            f"Source {idx} - {source['type'].upper()} "
+                            f"[{relevance_bar}] {relevance:.0%}"
+                        ):
+                            st.write(source['content'])
                 
-                st.success("✅ Search complete! Use results above to understand the document.")
+                print(f"\n✅ Answer generation complete!")
                 
         except Exception as e:
             st.error(f"❌ Error processing question: {e}")