Skip to content

Instantly share code, notes, and snippets.

@moheshmohan

moheshmohan/gist:6bf960a253e43e7e87e769f9c17f3fbe

Forked from mberman84/gist:9b3c281ae5e3e92b7e946f6a09787cde
Created January 14, 2024 08:40
Show Gist options
  • Save moheshmohan/6bf960a253e43e7e87e769f9c17f3fbe to your computer and use it in GitHub Desktop.
Save moheshmohan/6bf960a253e43e7e87e769f9c17f3fbe to your computer and use it in GitHub Desktop.
Download ZIP
PrivateGPT Installation
Raw
gistfile1.txt
# 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 dependencies
poetry install --with ui,local
# Download Embedding and LLM models
poetry run python scripts/setup
# (Optional) For Mac with Metal GPU, enable it. Check Installation and Settings section
to know how to enable GPU on other platforms
CMAKE_ARGS="-DLLAMA_METAL=on" pip install --force-reinstall --no-cache-dir llama-cpp-python
# 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/
@moheshmohan
Copy link
Author

moheshmohan commented Jan 14, 2024

to run next time go to folder

eval "$(pyenv init -)"

and then

Run the local server

PGPT_PROFILES=local make run

@moheshmohan
Copy link
Author

moheshmohan commented Jan 14, 2024

for activating poetry env

go to dir and then

poetry shell

@moheshmohan
Copy link
Author

moheshmohan commented Jan 14, 2024

adding docx2txt

poetry add docx2txt

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment