Update app.py

app.py

@@ -15,7 +15,7 @@ from llama_index.llms.llama_cpp.llama_utils import (
 )
 from llama_index.core.memory import ChatMemoryBuffer
 
-subprocess.run('pip install llama-cpp-python==0.2.75 --only-binary=:all: --extra-index-url=https://abetlen.github.io/llama-cpp-python/whl/cu124', env={'CMAKE_ARGS': "-DLLAMA_CUDA=on"}, shell=True)
+subprocess.run('pip install llama-cpp-python==0.2.75 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124', env={'CMAKE_ARGS': "-DLLAMA_CUDA=on"}, shell=True)
 
 hf_hub_download(repo_id="TheBloke/Mistral-7B-Instruct-v0.2-GGUF", filename="mistral-7b-instruct-v0.2.Q6_K.gguf",  local_dir = "./models")