gpt4all/gpt4all-bindings/python
2023-05-26 09:24:03 -04:00
..
docs Update index.md (#689) 2023-05-22 17:29:01 -07:00
gpt4all Add optional verbosity 2023-05-26 09:24:03 -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 Improvements to documentation (#606) 2023-05-16 15:29:27 -04:00
setup.py fixed response formatting when streaming 2023-05-18 12:02:11 -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

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 .
  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)