Update app.py

app.py

@@ -62,7 +62,7 @@ logger.info(f"Using n_threads: {recommended_threads}")
 try:
     llm = Llama(
         model_path=model_path,
-        n_ctx=1024,  # Context window size for the model (still needed, but not fully utilized for history)
+        n_ctx=2048,  # Context window size for the model (still needed, but not fully utilized for history)
         n_threads=recommended_threads,
         use_mlock=True,  # Lock model in RAM for faster access
         n_gpu_layers=0,  # CPU only