Update app.py

app.py

@@ -18,7 +18,7 @@ llm = LlamaCpp(
     model_path="Llama-3.1-8B-Instruct.Q5_K_M.gguf",
     temperature=0,
     max_tokens=512,
-    n_ctx = 8000,
+    n_ctx = 2000,
     top_p=1,
     # callback_manager=callback_manager,
     verbose=True,  # Verbose is required to pass to the callback manager