2023-08-10 11:29:54 +02:00
2023-08-05 14:42:38 +02:00
2023-05-07 14:02:19 +02:00
2023-04-07 18:02:36 +02:00
2023-04-07 15:14:34 +02:00
2023-08-10 11:29:54 +02:00
2023-04-07 15:14:34 +02:00

ChatMastermind

ChatMastermind is a Python application that automates conversation with AI, stores question-answer pairs with tags, and composes relevant chat history for the next question.

The project uses the OpenAI API to generate responses and stores the data in YAML files. It also allows you to filter chat history based on tags and supports autocompletion for tags.

Official repository URL: https://kaizenkodo.no/gitea/kaizenkodo/ChatMastermind.git

Requirements

  • Python 3.6 or higher
  • openai
  • PyYAML
  • argcomplete

You can install these requirements using pip:

pip install -r requirements.txt

Installation

You can install the package with the requirements using pip:

pip install .

Usage

cmm [-h] [-p PRINT | -q QUESTION | -D | -d | -l] [-c CONFIG] [-m MAX_TOKENS] [-T TEMPERATURE] [-M MODEL] [-n NUMBER] [-t [TAGS [TAGS ...]]] [-e [EXTAGS [EXTAGS ...]]] [-o [OTAGS [OTAGS ...]]] [-a] [-w] [-W]

Arguments

  • -p, --print: YAML file to print.
  • -q, --question: Question to ask.
  • -D, --chat-dump: Print chat history as a Python structure.
  • -d, --chat: Print chat history as readable text.
  • -a, --match-all-tags: All given tags must match when selecting chat history entries.
  • -w, --with-tags: Print chat history with tags.
  • -W, --with-tags: Print chat history with filenames.
  • -l, --list-tags: List all tags and their frequency.
  • -c, --config: Config file name (defaults to .config.yaml).
  • -m, --max-tokens: Max tokens to use.
  • -T, --temperature: Temperature to use.
  • -M, --model: Model to use.
  • -n, --number: Number of answers to produce (default is 3).
  • -t, --tags: List of tag names.
  • -e, --extags: List of tag names to exclude.
  • -o, --output-tags: List of output tag names (default is the input tags).

Examples

  1. Print the contents of a YAML file:
cmm -p example.yaml
  1. Ask a question:
cmm -q "What is the meaning of life?" -t philosophy -e religion
  1. Display the chat history as a Python structure:
cmm -D
  1. Display the chat history as readable text:
cmm -d
  1. Filter chat history by tags:
cmm -d -t tag1 tag2
  1. Exclude chat history by tags:
cmm -d -e tag3 tag4

Configuration

The configuration file (.config.yaml) should contain the following fields:

  • openai:
    • api_key: Your OpenAI API key.
    • model: The name of the OpenAI model to use (e.g. "text-davinci-002").
    • temperature: The temperature value for the model.
    • max_tokens: The maximum number of tokens for the model.
    • top_p: The top P value for the model.
    • frequency_penalty: The frequency penalty value.
    • presence_penalty: The presence penalty value.
  • system: The system message used to set the behavior of the AI.
  • db: The directory where the question-answer pairs are stored in YAML files.

Autocompletion

To activate autocompletion for tags, add the following line to your shell's configuration file (e.g., .bashrc, .zshrc, or .profile):

eval "$(register-python-argcomplete cmm)"

After adding this line, restart your shell or run source <your-shell-config-file> to enable autocompletion for the cmm script.

Contributing

Enable commit hooks

pip install pre-commit
pre-commit install

Execute tests before opening a PR

pytest

Consider using pyenv / pyenv-virtualenv

Short installation instructions:

  • install pyenv:
cd ~
git clone https://github.com/pyenv/pyenv .pyenv
cd ~/.pyenv && src/configure && make -C src
  • make sure that ~/.pyenv/shims and ~/.pyenv/bin are the first entries in your PATH, e. g. by setting it in ~/.bashrc
  • add the following to your ~/.bashrc (after setting PATH): eval "$(pyenv init -)"
  • create a new terminal or source the changes (e. g. source ~/.bashrc)
  • install virtualenv
git clone https://github.com/pyenv/pyenv-virtualenv.git $(pyenv root)/plugins/pyenv-virtualenv
  • add the following to your ~/.bashrc (after the commands above): eval "$(pyenv virtualenv-init -)
  • create a new terminal or source the changes (e. g. source ~/.bashrc)
  • go back to the ChatMasterMind repo and create a virtual environment with the latest Python, e. g. 3.11.4:
cd <CMM_REPO_PATH>
pyenv install 3.11.4
pyenv virtualenv 3.11.4 py311
pyenv activate py311

License

This project is licensed under the terms of the WTFPL License.

Description
Automate chatting with AI from command line, store and compose chat history for the next question
Readme 2.3 MiB
Languages
Python 99.3%
PHP 0.6%