git-llm 0.1.0

The project integrates Git with a llm (OpenAI, LlamaCpp, and GPT-4-All) to extend the capabilities of git.

git-llm

The project integrates Git with a llm (OpenAI, LlamaCpp, and GPT-4-All) to extend the capabilities of git.

Description

git-llm is a tool that allows you to generate changelog entries, and other things using OpenAI, LlamaCpp, and GPT-4-All. It supports offline processing using GPT4All without sharing your code with third parties, or you can use OpenAI if privacy is not a concern for you. It is only recommended for educational purposes and not for production use.

Installation

To install git-llm, you need to have Python 3.9 and an OpenAI API key api-keys. Additionally, if you want to use the GPT4All model, you need to download the ggml-gpt4all-j-v1.3-groovy.bin model. If you prefer a different model, you can download it from GPT4All and configure path to it in the configuration and specify its path in the configuration. If you want some files to be ignored, add them to .gitignore.

To install git-llm, run the following command in your terminal:

pip install git-llm

Once git-llm is installed, you can run it from the command line:

talk-codebase config

You can also edit the configuration manually by editing the ~/.git_llm_config.yaml file. If for some reason you cannot find the configuration file, just run the tool and at the very beginning it will output the path to the configuration file.

# The OpenAI API key. You can get it from https://beta.openai.com/account/api-keys
api_key: sk-xxx
# maximum size of a chunk of text to be sent to the model
chunk_size: 500
# the maximum tokens
max_tokens: 1048
# model name for the OpenAI API
model_name: gpt-3.5-turbo
# model path for the local model
model_path: models/ggml-gpt4all-j-v1.3-groovy.bin
# model type: openai or local
model_type: openai

Features

More commands will be added in the future.

Contributing

Contributions are always welcome!