fix: use llama-4-scout highest free tier TPM

app.py

@@ -139,7 +139,7 @@ def generate_followups(query, answer):
     ]
 
 def get_llm():
-    return ChatGroq(api_key=os.environ.get("GROQ_API_KEY"), model="llama3-8b-8192", temperature=0.1)
+    return ChatGroq(api_key=os.environ.get("GROQ_API_KEY"), model="llama-4-scout-17b-16e-instruct", temperature=0.1)
 
 def create_crew(pdf_tool):
     llm = get_llm()