gpt4all/gpt4all-bindings/python/README.md

Python GPT4All

This package contains a set of Python bindings that runs the llmodel C-API.

Local Installation Instructions

TODO: Right now instructions in main README still depend on Qt6 setup. To setup Python bindings, we just need llmodel to be built which is much simpler. However, in the future, the below installation instructions should be sequentially organized such that we expect the main README's instructions were followed first.

1. Setup llmodel

git clone --recurse-submodules https://github.com/nomic-ai/gpt4all
cd gpt4all-backend/llmodel/
mkdir build
cd build
cmake ..
cmake --build . --parallel

Confirm that libllmodel.* exists in gpt4all-backend/llmodel/build.

2. Setup Python package

cd ../../gpt4all-bindings/python
pip3 install -r requirements.txt
pip3 install -e .

3. Test it out! In a Python script or console:

from gpt4all import GPT4All

gptj = GPT4All("ggml-gpt4all-j-v1.3-groovy")
messages = [{"role": "user", "content": "Name 3 colors"}]
gptj.chat_completion(messages)