Update app.py

app.py

@@ -311,27 +311,18 @@ class OptimizedGazaRAGSystem:
 
     
     def _initialize_llm(self):
-    """Initialize FLAN-T5 model (CPU-friendly)"""
-    model_name = "google/flan-t5-base"
-    try:
-        logger.info(f"🔄 Loading fallback CPU model: {model_name}")
-
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.llm = AutoModelForCausalLM.from_pretrained(model_name)
-
-        self.generation_pipeline = pipeline(
-            "text2text-generation",  # <-- Important for T5!
-            model=self.llm,
-            tokenizer=self.tokenizer,
-            return_full_text=False
-        )
-
-        logger.info("✅ FLAN-T5 model loaded successfully")
-
-    except Exception as e:
-        logger.error(f"❌ Error loading FLAN-T5 model: {e}")
-        self.llm = None
-        self.generation_pipeline = None
+        """Initialize FLAN-T5 model (CPU-friendly)"""
+        model_name = "google/flan-t5-base"
+        try:
+            logger.info(f"🔄 Loading fallback CPU model: {model_name}")
+            self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+            self.llm = AutoModelForCausalLM.from_pretrained(model_name)
+            self.generation_pipeline = pipeline("text2text-generation", model=self.llm,tokenizer=self.tokenizer,return_full_text=False)
+            logger.info("✅ FLAN-T5 model loaded successfully")
+        except Exception as e:
+            logger.error(f"❌ Error loading FLAN-T5 model: {e}")
+            self.llm = None
+            self.generation_pipeline = None