Skip to main content

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

The easiest way to install the Python bindings for GPT4All is to use pip:

pip install gpt4all

This will download the latest version of the gpt4all package from PyPI.

Local Build

As an alternative to downloading via pip, you may build the Python bindings from source.

Prerequisites

On Windows and Linux, building GPT4All requires the complete Vulkan SDK. You may download it from here: https://vulkan.lunarg.com/sdk/home

macOS users do not need Vulkan, as GPT4All will use Metal instead.

Building the python bindings

  1. Clone GPT4All and change directory:
git clone --recurse-submodules https://github.com/nomic-ai/gpt4all.git
cd gpt4all/gpt4all-backend
  1. Build the backend.

If you are using Windows and have Visual Studio installed:

cmake -B build
cmake --build build --parallel --config RelWithDebInfo

For all other platforms:

cmake -B build -DCMAKE_BUILD_TYPE=RelWithDebInfo
cmake --build build --parallel

RelWithDebInfo is a good default, but you can also use Release or Debug depending on the situation.

  1. Install the Python package:
cd ../../gpt4all-bindings/python
pip install -e .

Usage

Test it out! In a Python script or console:

from gpt4all import GPT4All
model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf")
output = model.generate("The capital of France is ", max_tokens=3)
print(output)

GPU Usage

from gpt4all import GPT4All
model = GPT4All("orca-mini-3b-gguf2-q4_0.gguf", device='gpu') # device='amd', device='intel'
output = model.generate("The capital of France is ", max_tokens=3)
print(output)

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.

Release files for gpt4all 2.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for gpt4all 2.5.1
File Interpreter ABI Platform
gpt4all-2.5.1-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details
gpt4all-2.5.1-py3-none-manylinux1_x86_64.whl Python 3 none Linux glibc 2.5+ x86-64 Details
gpt4all-2.5.1-py3-none-macosx_10_15_universal2.whl Python 3 none macOS 10.15+ universal2 (ARM64, x86-64) Details

Total release size: 16.0 MB

Release files / gpt4all-2.5.1-py3-none-win_amd64.whl

Download URL gpt4all-2.5.1-py3-none-win_amd64.whl
Size 6.3 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
28b3d2dbc0dcdb731ade227a098cbba8201f98bb9871811fa656811e93302737
BLAKE2b-256 checksum
How to use checksums
1536a227f0ce3d2bf1cc516e017311bdda89321e9536c75b692e1272cc885121
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.8.12

Release files / gpt4all-2.5.1-py3-none-manylinux1_x86_64.whl

Download URL gpt4all-2.5.1-py3-none-manylinux1_x86_64.whl
Size 3.9 MB
Tags Linux glibc 2.5+ x86-64 Python 3
SHA-256 checksum
How to use checksums
50c41cf0b5cd1c5701d67075f002aa924abd3a99cf6f9f41864c78f65abb8cd0
BLAKE2b-256 checksum
How to use checksums
af6f1f033f7d0b6711d19abc928b193c3db301fe2b7945dc2da5e683bce789f4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.8.12

Release files / gpt4all-2.5.1-py3-none-macosx_10_15_universal2.whl

Download URL gpt4all-2.5.1-py3-none-macosx_10_15_universal2.whl
Size 5.9 MB
Tags Python 3 macOS 10.15+ universal2 (ARM64, x86-64)
SHA-256 checksum
How to use checksums
c865df2076b3c7863b51e4d0121023d6c3d2e60ba2d1df3d6b49c2222f4fbb72
BLAKE2b-256 checksum
How to use checksums
ee43a59f6f62d097e27bab7cc0b5eb09b757382aa8e7d6641e6f6522e1a5f74d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.8.12

Release history Release notifications | RSS feed

2.8.2

3 release files

2.8.1

3 release files

2.8.0

1 release file

2.7.0

3 release files

2.6.0

3 release files

This release

2.5.1 This release

3 release files

2.5.0

3 release files

2.4.0

3 release files

2.3.2

3 release files

2.3.1

3 release files

2.3.0

3 release files

2.2.1

3 release files

2.2.0

3 release files

2.1.0

3 release files

2.0.2

3 release files

2.0.1

3 release files

2.0.0

3 release files

1.0.12

3 release files

1.0.11

3 release files

1.0.10

3 release files

1.0.9

3 release files

1.0.8

3 release files

1.0.7

3 release files

1.0.6

3 release files

1.0.5

3 release files

1.0.4

3 release files

1.0.3

3 release files

1.0.2

3 release files

1.0.1

3 release files

1.0.0

3 release files

0.3.6

3 release files

0.3.5

3 release files

0.3.4

3 release files

0.3.3

3 release files

0.3.2

3 release files

0.3.0

3 release files

0.2.3

3 release files

0.2.1

3 release files

0.2.0

3 release files

0.1.9

3 release files

0.1.8

3 release files

0.1.7

1 release file

0.1.6

1 release file

0.1.5

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page