gpt4all/gpt4all-bindings/python
2023-06-12 23:11:54 -04:00
..
docs Update gpt4all_faq.md (#861) 2023-06-05 15:41:30 -04:00
gpt4all Generator in Python Bindings - streaming yields tokens at a time (#895) 2023-06-09 10:17:44 -04:00
tests [DATALAD RUNCMD] run codespell throughout 2023-05-16 11:33:59 -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 GPT4All Updated Docs and FAQ (#632) 2023-05-18 16:07:57 -04:00
README.md Move usage in Python bindings readme to own section (#907) 2023-06-09 10:13:35 +02:00
setup.py version bump 2023-06-12 17:32:56 -04:00

Python GPT4All

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

Package on PyPI: https://pypi.org/project/gpt4all/

Documentation

https://docs.gpt4all.io/gpt4all_python.html

Installation

pip install gpt4all

Local Build Instructions

NOTE: If you are doing this on a Windows machine, you must build the GPT4All backend using MinGW64 compiler.

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

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

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

Usage

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)