update LLM for response generation

app.py

@@ -790,7 +790,8 @@ def respond(
         # Stream response
         response = client.chat.completions.create(
             messages=[{"role": "user", "content": prompt}],
-            model="deepseek-r1-distill-llama-70b",
+            model="llama-3.1-8b-instant",
+            # model="llama-3.3-70b-versatile",
             stream=True,
         )
         cumulative_response = ""  # Keep track of the cumulative response