A simple assistant for Mac that uses llama-cpp-python to assist you on your predefined needs. This uses pretty much 90% of the code from here but replaces the ollama stuff with llama-cpp-python.
Because I wanted a more pythonic solution and wanted to build something w/ llama-cpp-python.
Create a virtual environment and follow the steps below.
- Install llama-cpp-python
CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python
Note: If you are on CUDA/ CPU, you can remove the CMAKE_ARGS="-DGGML_METAL=on" part and replace with appropriate cmake args here.
- Install pynput and pyperclip
pip install pynput pyperclip
- Run main.py
Note: These steps are for macos. If you are on windows or linux, you will need to install llama-cpp-python differently.