Local install still requires llama_cpp even if I'm using the vanilla install

[kyutums]

I am trying out the vanilla install using instructions from https://docs.privategpt.dev/installation. However, I am getting errors when I get to the make run bit. The start of the errors is:
23:46:00.323 [INFO ] private_gpt.settings.settings_loader - Starting application with profiles=['default'] 23:46:02.156 [INFO ] private_gpt.components.llm.llm_component - Initializing the LLM in mode=local Traceback (most recent call last): File "/home/pocket_advanced/.cache/pypoetry/virtualenvs/private-gpt-1k29Sc9X-py3.11/lib/python3.11/site-packages/injector/__init__.py", line 798, in get return self._context[key] ~~~~~~~~~~~~~^^^^^ KeyError: <class 'private_gpt.ui.ui.PrivateGptUi'>

... while the list bit is ...

ImportError: Could not import llama_cpp library.Please install llama_cpp with pip install llama-cpp-python.See the full installation guide for GPU support at https://github.com/abetlen/llama-cpp-python`
make: *** [Makefile:36: run] Error 1`

I'm trying to install it on a local Linux server running Ubuntu. No GPU.

[kyutums]

It's working now. I had to install via poetry run python scripts/setup