Update src/rag_engine.py

src/rag_engine.py

@@ -19,8 +19,8 @@ clip_model.eval().to("cpu")
 
 qa_pipeline = pipeline(
     "text2text-generation",
-    model="google/flan-t5-base",
-    tokenizer="google/flan-t5-base",
+    model="google/flan-t5-small",
+    tokenizer="google/flan-t5-small",
     device=-1  # CPU
 )