Import error asking me to `pip install llama-cpp-python` even though its already installed

[that-one-arab]

trafficstars

When running the python -m private_gpt command I get the below error

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`

I am using ubuntu 20.04, and using virtualenvwrapper as my python environment manager.

[he-man86]

I have the same issue when installing via docker compose build. Have not been able to solve it so far. Idea's are welcome!

[that-one-arab]

@he-man86 I wasn't using docker though

[thanhtung100397]

I have tried this command and it's worked (i'm using GPU support build) CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python

[rajni-keyss]

I am having the same issue. any solutions will be helpful

[mbianchidev]

Try looking into my latest PR: https://github.com/imartinez/privateGPT/pull/1428/

I basically fixed this error by downloading the model from docker with an entrypoint.sh script @he-man86

If you are not using docker usually running the setup script suffices. https://github.com/imartinez/privateGPT/blob/main/scripts/setup @that-one-arab

For doc see: https://docs.privategpt.dev/overview/welcome/quickstart

git clone https://github.com/imartinez/privateGPT && cd privateGPT && \
python3.11 -m venv .venv && source .venv/bin/activate && \
pip install --upgrade pip poetry && poetry install --with ui,local && ./scripts/setup

# Launch the privateGPT API server **and** the gradio UI
python3.11 -m private_gpt

# In another terminal, create a new browser window on your private GPT!
open http:////127.0.0.1:8001/

[github-actions[bot]]

Stale issue

[copeland3300]

Running into this on Windows 10. Any suggestions?

[italocjs]

Same issue here under wsl

[MarkChrisE2091]

Still happening on windows10

[fernandodiacenco]

Happens on a clean Debian 12 install as well.

[italocjs]

I have followed this guide and managed to install it https://www.youtube.com/watch?v=VXMlf8tADxg&t=426s

[dipakbg145]

Could not load Llama model from path: /media1_TB/datasets/Dip_current_project/Chat_bot_Project/Llama_Chat_Bot/Birbal_Voice_Assistant_Web/model/llama-2-7b-chat.ggmlv3.q8_0.bin. Received error Failed to load model from file: /media/1_TB/datasets/Dip_current_project/Chat_bot_Project/Llama_Chat_Bot/Birbal_Voice_Assistant_Web/model/llama-2-7b-chat.ggmlv3.q8_0.bin (type=value_error) how to resolve this error