Update app.py

app.py

@@ -2,7 +2,8 @@ import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from retriever.vectordb_rerank import search_documents  # 🧠 RAG 검색기 불러오기
+# from retriever.vectordb_rerank import search_documents  # 🧠 RAG 검색기 불러오기
+from services.rag_pipeline import rag_pipeline
 
 model_name = "dasomaru/gemma-3-4bit-it-demo"
 
@@ -57,5 +58,9 @@ def generate_response(query):
 
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-demo = gr.Interface(fn=generate_response, inputs="text", outputs="text")
+@spaces.GPU(duration=300)
+def generate_response_with_pipeline(query):
+    return rag_pipeline(query)    
+
+demo = gr.Interface(fn=generate_response_with_pipeline, inputs="text", outputs="text")
 demo.launch()