pyRobBot
Chat with GPT LLMs over voice, UI & terminal.
All with access to the internet.

PyRobBot is a python package that uses OpenAI's GPT large language models (LLMs) to implement:

• A fully configurable personal assistant that can speak and listen to you
• An equally fully configurable text-based chatbot that can be used either via web UI or terminal

Features

• Personal assistant with text-to-speech and speech-to-text capabilities
  • Talk to the GPT assistant and the assistant will talk back to you!
  • Choose your preferred language (e.g., rob --lang pt-br)
  • Choose your preferred Text-to-Speech (TTS) engine (e.g., rob --tts google)
    • OpenAI Text-to-Speech (default): AI-generated human-like voice
    • Google TTS: free at the time being, with decent quality
  • Choose your preferred Speech-to-Text (STT) engine
    • Also between OpenAI and Google (default)
• Web browser UI (made with Streamlit)
  • Add/remove conversations dynamically
  • Automatic/editable conversation summary title
  • Input via text or voice
• Terminal UI
  • For a more "Wake up, Neo" experience
• Internet access: The assistent will search the web and to find the answers it doesn't have in its training data
  • E.g. current events, weather forecasts, etc.
• Fully configurable
  • Support for multiple GPT LLMs
  • Control over the parameters passed to the OpenAI API, with (hopefully) sensible defaults
  • Ability to pass base directives to the LLM
    • E.g., to make it adopt a persona, but you decide which directived to pass
  • Dynamically modifiable AI parameters in each chat separately
    • No need to restart the chat
• Autosave & retrieve chat history
  • In the browser UI, you can even read the transcripts of your voice conversations with the AI
• Chat context handling using embeddings
• Estimated API token usage and associated costs
• OpenAI API key is never stored on disk

System Requirements

• Python >= 3.9
• A valid OpenAI API key
  • Set in the Web UI or through the environment variable OPENAI_API_KEY
• To enable voice chat, you also need:
  • PortAudio
    • Install on Ubuntu with sudo apt-get --assume-yes install portaudio19-dev python-all-dev
    • Install on CentOS/RHEL with sudo yum install portaudio portaudio-devel
  • ffmpeg
    • Install on Ubuntu with sudo apt-get --assume-yes install ffmpeg
    • Install on CentOS/RHEL with sudo yum install ffmpeg

Installation

This, naturally, assumes your system fulfills all requirements.

Using pip

pip install pyrobbot

From source

pip install git+https://github.com/paulovcmedeiros/pyRobBot.git

Basic Usage

Upon succesfull installation, you should be able to run

rob [opts] SUBCOMMAND [subcommand_opts]

where [opts] and [subcommand_opts] denote optional command line arguments that apply, respectively, to rob in general and to SUBCOMMAND specifically.

Please run rob -h for information about the supported subcommands and general rob options. For info about specific subcommands and the options that apply to them only, please run rob SUBCOMMAND -h (note that the -h goes after the subcommand in this case).

Chatting by Voice (default)

rob

Using the Web UI

rob ui

See also our demo Streamlit app!

Running on the Terminal

rob .

Disclaimers

This project's main purpose has been to serve as a learning exercise for me, as well as tool for experimenting with OpenAI API, GPT LLMs and text-to-speech/speech-to-text.

While it does not claim to be the best or more robust OpenAI-powered chatbot out there, it does aim to provide a friendly user interface that is easy to install, use and configure.

Feel free to open an issue or, even better, submit a pull request if you find a bug or have a suggestion.

Last but not least: This project is independently developed and not affiliated, endorsed, or sponsored by OpenAI in any way. It is separate and distinct from OpenAI’s own products and services.