You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

History

385olt b4dbbd1485 Python bindings: Custom callbacks, chat session improvement, refactoring (#1145 ) * Added the following features: \n 1) Now prompt_model uses the positional argument callback to return the response tokens. \n 2) Due to the callback argument of prompt_model, prompt_model_streaming only manages the queue and threading now, which reduces duplication of the code. \n 3) Added optional verbose argument to prompt_model which prints out the prompt that is passed to the model. \n 4) Chat sessions can now have a header, i.e. an instruction before the transcript of the conversation. The header is set at the creation of the chat session context. \n 5) generate function now accepts an optional callback. \n 6) When streaming and using chat session, the user doesn't need to save assistant's messages by himself. This is done automatically. * added _empty_response_callback so I don't have to check if callback is None * added docs * now if the callback stop generation, the last token is ignored * fixed type hints, reimplemented chat session header as a system prompt, minor refactoring, docs: removed section about manual update of chat session for streaming * forgot to add some type hints! * keep the config of the model in GPT4All class which is taken from models.json if the download is allowed * During chat sessions, the model-specific systemPrompt and promptTemplate are applied. * implemented the changes * Fixed typing. Now the user can set a prompt template that will be applied even outside of a chat session. The template can also have multiple placeholders that can be filled by passing a dictionary to the generate function * reversed some changes concerning the prompt templates and their functionality * fixed some type hints, changed list[float] to List[Float] * fixed type hints, changed List[Float] to List[float] * fix typo in the comment: Pepare => Prepare --------- Signed-off-by: 385olt <385olt@gmail.com>		1 year ago
..
docs	Python bindings: Custom callbacks, chat session improvement, refactoring (#1145 )	1 year ago
gpt4all	Python bindings: Custom callbacks, chat session improvement, refactoring (#1145 )	1 year ago
.gitignore	…
.isort.cfg	…
LICENSE.txt	…
MANIFEST.in	…
README.md	…
makefile	…
mkdocs.yml	…
setup.py	…

README.md

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 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.

Setup Python package

cd ../../gpt4all-bindings/python
pip3 install -e .

Usage

Test it out! In a Python script or console:

from gpt4all import GPT4All
model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin")
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.