added ZeroGPU support

app.py

@@ -7,6 +7,7 @@ from tqdm import tqdm
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
+import spaces
 
 # Ensure an HF Token is present for gated models (like Llama 3)
 HF_TOKEN = os.getenv("HF_TOKEN")
@@ -126,6 +127,7 @@ except Exception as e:
     print(f"Error initializing RAG: {e}")
 
 # --- GRADIO INTERFACE ---
+@spaces.GPU(duration=10)
 def chat_function(message, history):
     if rag is None:
         return "System Error: The RAG pipeline failed to initialize. Check logs and ensure the 'index/' folder is uploaded."

requirements.txt

@@ -7,4 +7,5 @@ langchain-community
 faiss-gpu
 numpy<2
 tqdm
-sentence_transformers
+sentence_transformers
+spaces