ket0x4 / ketard-ai

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Ketard AI Bot

Overview

Ket.ai is an overengineered telegram bot that functions as a chatbot and system status monitor. It is built using the pyrogram library and includes a variety of commands for generating responses using various APIs and local LLMs. The bot is designed to be easily configurable and extensible, with support for custom commands and system information reporting.

Features

  • System Information: Commands to check CPU usage, RAM usage, and system temperature.
  • Text Generation: Utilizes the Ollama API for generating responses based on user input.
  • Debug and Status Modes: Includes configurations for debug mode and system status reporting.
  • Command Handling: Custom commands for different functionalities, including help and start commands.

Requirements

  • Python3
  • GNU+Linux
  • Ollama (for local llm models)
  • ffmpeg and flac (for speech-to-text)

Usage

  • Start Command: /start to get an introduction and available commands.
  • Help Command: /help provides information on how to use the bot and its commands.
  • Status Command: /status to get the current system status including CPU usage, RAM usage, and more.
  • Custom Commands: {DataConfig.GEN_COMMANDS} for generating responses based on specified commands.
  • Sum Command: /sum pass youtube video url to get a summary of the video.

Installation

Click to view installation steps.
  1. Clone the repository:
    git clone https://github.com/ket0x4/ketard-ai.git && cd ketard-ai
  2. Create a virtual environment:
    python -m venv venv
  3. Activate the virtual environment:
    source venv/bin/activate
  4. Install the dependencies:
    pip install -r requirements.txt
  5. Create a configuration file and fill in the required variables:
    cp sample_config.json config.json
  6. Configure the bot by editing the config.json file with the appropriate values for BOT_NAME, API_ID, API_HASH, BOT_TOKEN, ...
  7. Run the bot:
    bash start

Configuration

Ensure that your config.json is correctly set up with the necessary API credentials and configurations for bot behavior.

To-do

Click to expand!
  • Add /sum command
  • Async /sum command
  • Support other youtube url's
  • Add speech-to-text support
  • Check api response before sending
  • Fix async /status command
  • Add blacklist support
  • log prompts and responses to db
  • split long messages
  • delete status message after sending prompt response
  • Add reply support
  • Refactor code
  • remove repeated code
  • Add TR lang support to /sum command
  • Better /help message
  • Add /start command
  • Make llm backend configurable
  • Add /model command for changing llm model
  • Add /debug command for enabling debug mode
  • Fix /update command

License

This project is licensed under the terms of the GNU General Public License v3.0.

About

License:GNU General Public License v3.0


Languages

Language:Python 98.1%Language:Dockerfile 1.9%