Files
gpt4all/gpt4all-bindings/python
Andriy Mulyar 8bf1e5abbd Update index.md (#689)
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-05-22 17:29:01 -07:00
..
2023-05-22 17:29:01 -07:00
2023-05-10 13:38:32 -04:00
2023-05-10 13:38:32 -04:00
2023-05-10 13:38:32 -04:00
2023-05-10 13:38:32 -04:00
2023-05-18 16:07:57 -04:00
2023-05-16 15:29:27 -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)