Update app.py

app.py

@@ -4,6 +4,13 @@ from llama_index.core import Settings
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 import torch
 import spaces
+import subprocess
+
+subprocess.run(
+     "pip install flash-attn --no-build-isolation",
+     env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
+     shell=True,
+)
 
 
 documents = SimpleDirectoryReader("./data").load_data()