Update src/streamlit_app.py

src/streamlit_app.py

@@ -24,7 +24,7 @@ st.set_page_config(
 )
 
 COLLECTION_NAME = "math_knowledge_base"
-DATASET_REPO = "yourusername/math-ai-documents"  # ← CHANGE THIS!
+DATASET_REPO = "Hebaelsayed/math-ai-documents"  
 
 # ============================================================================
 # AVAILABLE EMBEDDING MODELS
@@ -782,4 +782,92 @@ with tab2:
             
             with st.spinner("Generating solution..."):
                 
-                context = "\n\n".join([r
+                context = "\n\n".join([r.payload['content'] for r in results])
+                
+                prompt = f"""Solve this problem using references.
+
+PROBLEM: {problem}
+
+REFERENCES: {context}
+
+DETAIL: {detail}
+
+FORMAT:
+## SOLUTION
+[Steps]
+
+## REASONING
+[Why this approach]
+
+## REFERENCES
+[Which sources helped]"""
+
+                try:
+                    message = claude.messages.create(
+                        model="claude-sonnet-4-20250514",
+                        max_tokens=4000,
+                        messages=[{"role": "user", "content": prompt}]
+                    )
+                    
+                    st.markdown("---")
+                    st.markdown(message.content[0].text)
+                    
+                    st.download_button(
+                        "📥 Download Solution",
+                        message.content[0].text,
+                        file_name=f"solution_{int(time.time())}.md"
+                    )
+                
+                except Exception as e:
+                    st.error(f"Error: {e}")
+
+# ============================================================================
+# TAB 3: STATISTICS
+# ============================================================================
+
+with tab3:
+    
+    st.title("📈 Statistics & Analytics")
+    
+    try:
+        sample = qdrant.scroll(
+            collection_name=COLLECTION_NAME,
+            limit=1000,
+            with_payload=True,
+            with_vectors=False
+        )
+        
+        if sample and sample[0]:
+            types = {}
+            sources = set()
+            
+            for point in sample[0]:
+                src_type = point.payload.get('source_type', 'unknown')
+                types[src_type] = types.get(src_type, 0) + 1
+                sources.add(point.payload.get('source_name', 'Unknown'))
+            
+            col1, col2, col3 = st.columns(3)
+            
+            with col1:
+                st.metric("Total Vectors", get_vector_count(qdrant))
+            
+            with col2:
+                st.metric("Unique Sources", len(sources))
+            
+            with col3:
+                st.metric("Document Types", len(types))
+            
+            st.subheader("Distribution by Type")
+            for doc_type, count in sorted(types.items()):
+                pct = count / sum(types.values()) * 100
+                st.progress(count / sum(types.values()), text=f"{doc_type}: {count} ({pct:.1f}%)")
+            
+            st.subheader("All Sources")
+            for src in sorted(sources):
+                st.caption(f"• {src}")
+    
+    except Exception as e:
+        st.error(f"Error: {e}")
+
+st.sidebar.markdown("---")
+st.sidebar.caption("v2.0 - Production")