PrivateGPT Installation on WSL2

gistfile1.txt

# Install CUDA runtime from https://docs.nvidia.com/cuda/wsl-user-guide/index.html
# Install pyenv from https://bgasparotto.com/install-pyenv-ubuntu-debian

# Clone the repo
git clone https://github.com/imartinez/privateGPT
cd privateGPT

# Install Python 3.11
pyenv install 3.11
pyenv local 3.11

# Install Poetry
pip install poetry

# Install dependencies
poetry install --with ui,local

# Download Embedding and LLM models
poetry run python scripts/setup

# To Run on GPU (with CUDA 12)
CUDACXX=/usr/local/cuda-12/bin/nvcc CMAKE_ARGS="-DLLAMA_CUBLAS=on -DCMAKE_CUDA_ARCHITECTURES=native" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir --force-reinstall --upgrade

# Run the local server  
PGPT_PROFILES=local make run

# Note: on Mac with Metal you should see a ggml_metal_add_buffer log, stating GPU is 
being used

# Navigate to the UI and try it out! 
http://localhost:8001/