changed Llama model due to rate limit

agent.py

@@ -19,7 +19,7 @@ from langgraph.checkpoint.memory import MemorySaver
 def get_llm():
     """Get Groq LLM instance"""
     return ChatGroq(
-        model="llama-3.3-70b-versatile",
+        model="llama-3.1-8b-instant",
         temperature=0,
         max_tokens=8000,
         timeout=60,