This project provides a feature-rich Telegram bot that leverages OpenAI's API to offer ChatGPT-like conversational experiences. It targets users seeking a more responsive, flexible, and feature-packed alternative to the official ChatGPT web interface, enabling self-hosting for enhanced control and customization.

How It Works

The bot integrates with OpenAI's API, supporting various models including GPT-4 and GPT-4 Turbo, and offers features like message streaming for lower perceived latency. It includes specialized "chat modes" defined in a YAML configuration file, allowing users to tailor the bot's persona and functionality for specific tasks like coding assistance, artistic generation (via DALL-E 2), or acting as a psychologist.

Quick Start & Requirements

• Install via Docker: docker-compose --env-file config/config.env up --build
• Prerequisites: OpenAI API key, Telegram bot token from @BotFather.
• Configuration: Edit config/config.example.yml and config/config.example.env.
• Documentation: Bot commands

Highlighted Details

• Supports GPT-4, GPT-4 Turbo, and GPT-4 Vision.
• Features message streaming for real-time responses.
• Includes 15+ specialized chat modes and custom mode creation.
• Integrates DALL-E 2 for image generation and Whisper API for voice message recognition.
• Supports group chats and OpenAI API base URL configuration for compatibility with services like LocalAI.

Maintenance & Community

• Maintained by @karfly.
• Community support via Discord/Slack is not explicitly mentioned.

Licensing & Compatibility

• The README does not specify a license. This requires clarification for commercial use or integration into closed-source projects.

Limitations & Caveats

The project's licensing is not specified, which may pose a barrier to commercial adoption or use within proprietary software. Community support channels are not detailed in the README.