gpt4all/gpt4all-bindings/python

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 git@github.com:nomic-ai/gpt4all.git
cd gpt4all/gpt4all-backend/
mkdir build
cd build
cmake ..
cmake --build . --parallel

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

2. 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)

Troubleshooting a Local Build

• If you're on Windows and have compiled with a MinGW toolchain, you might run into an error like:

  FileNotFoundError: Could not find module '<...>\gpt4all-bindings\python\gpt4all\llmodel_DO_NOT_MODIFY\build\libllmodel.dll'
  (or one of its dependencies). Try using the full path with constructor syntax.
  

  The key phrase in this case is "or one of its dependencies". The Python interpreter you're using probably doesn't see the MinGW runtime dependencies. At the moment, the following three are required: libgcc_s_seh-1.dll, libstdc++-6.dll and libwinpthread-1.dll. You should copy them from MinGW into a folder where Python will see them, preferably next to libllmodel.dll.

• Note regarding the Microsoft toolchain: Compiling with MSVC is possible, but not the official way to go about it at the moment. MSVC doesn't produce DLLs with a lib prefix, which the bindings expect. You'd have to amend that yourself.