gpt4all/gpt4all-bindings/python
2023-05-12 15:21:56 -04:00
..
docs documentation and cleanup 2023-05-11 11:02:44 -04:00
gpt4all mpt pypi job 2023-05-12 15:21:56 -04:00
tests mpt bindings 2023-05-12 15:21:56 -04:00
.gitignore transfer python bindings code 2023-05-10 13:38:32 -04:00
LICENSE.txt transfer python bindings code 2023-05-10 13:38:32 -04:00
makefile transfer python bindings code 2023-05-10 13:38:32 -04:00
MANIFEST.in transfer python bindings code 2023-05-10 13:38:32 -04:00
mkdocs.yml documentation and cleanup 2023-05-11 11:02:44 -04:00
README.md working circleci and updated readme 2023-05-12 10:47:46 -04:00
setup.py mpt pypi job 2023-05-12 15:21:56 -04:00

Python GPT4All

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

Documentation

docs.gpt4all.io

Installation

pip install gpt4all

Local Build Instructions

  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.

  1. Setup Python package
cd ../../gpt4all-bindings/python
pip3 install -e .
  1. 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)