AI/gpt4all

mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00

Claudius Ellsel 3c1b59f5c6

Move usage in Python bindings readme to own section (#907 )

Have own section for short usage example, as it is not specific to local build

Signed-off-by: Claudius Ellsel <claudius.ellsel@live.de>

2023-06-09 10:13:35 +02:00

990 B

Raw Permalink Blame History

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.

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.

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)

990 B Raw Permalink Blame History