Upload app.py

app.py

@@ -36,7 +36,7 @@ ENABLE_ENHANCED_RAG = True  # Enable enhanced RAG system for Google Drive
 RAG_CONFIDENCE_THRESHOLD = 0.95  # 95% threshold for saving to RAG
 
 # Cloud Storage Configuration
-USE_CLOUD_STORAGE = True  # Set to True to use cloud storage instead of local DB
+USE_CLOUD_STORAGE = False  # Disabled - using Enhanced RAG system instead (no duplicates)
 CLOUD_STORAGE_TYPE = "google_drive"  # Options: "google_drive", "google_cloud", "local"
 GOOGLE_DRIVE_FILE_ID = None  # Will be set when file is created
 
@@ -555,11 +555,16 @@ def populate_knowledge_base_from_training_data():
         
         return True
         
+    except FileNotFoundError as e:
+        print(f"⚠️ Training data file not found: {e}")
+        print("   Knowledge base will start empty (this is OK)")
+        return False
     except Exception as e:
-        print(f"❌ Error populating knowledge base: {e}")
+        print(f"⚠️ Error populating knowledge base: {e}")
+        print("   Knowledge base will start empty (this is OK)")
         return False
 
-# Populate knowledge base with training data on startup
+# Populate knowledge base with training data on startup (optional)
 print("🚀 Populating knowledge base with training data...")
 populate_knowledge_base_from_training_data()
 
@@ -1553,25 +1558,8 @@ def analyze_news(news_text):
             if gemini_analysis:
                 print(f"   Analysis preview: {gemini_analysis[:300]}...")
 
-        if gemini_max_confidence and gemini_max_confidence >= CONFIDENCE_THRESHOLD:
-            print(f"🚀 High Gemini confidence detected ({gemini_max_confidence:.1%}) - adding to knowledge base for RAG...")
-            final_prediction = "REAL" if gemini_real_percent > gemini_fake_percent else "FAKE"
-            
-            # Add to knowledge base
-            success = add_to_knowledge_base(
-                news_text=news_text,
-                prediction=final_prediction,
-                confidence=gemini_max_confidence,  # Use Gemini confidence for RAG storage
-                search_results=search_results,
-                gemini_analysis=gemini_analysis
-            )
-            
-            if success:
-                print("✅ Successfully added to knowledge base for future RAG retrieval!")
-            else:
-                print("⚠️ Failed to add to knowledge base (duplicate or error)")
-        
-        # Step 8: Enhanced RAG System - Save to Google Drive if confidence is high enough
+        # Step 7: Enhanced RAG System - Save to Google Drive if confidence is high enough
+        # (Old knowledge base system disabled to avoid duplicates - Enhanced RAG is better)
         print(f"\n🔍 RAG SAVE DEBUG:")
         print(f"   ENABLE_ENHANCED_RAG: {ENABLE_ENHANCED_RAG}")
         print(f"   gemini_max_confidence: {gemini_max_confidence} ({gemini_max_confidence:.1%} if > 0)")