This project provides a serverless Telegram bot that allows users to interact with ChatGPT, leveraging the new ChatGPT API. It's designed for users who want a readily deployable AI chatbot experience without managing server infrastructure, offering features like voice message support and Markdown rendering.

How It Works

The bot is built using AWS Lambda and the Chalice framework, enabling a fully serverless architecture. It processes incoming Telegram messages, forwards them to the OpenAI API for ChatGPT processing, and returns the responses to Telegram. Voice messages are handled by storing audio files in an AWS S3 bucket before processing.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Deploy using Chalice: chalice deploy
• Requires AWS account, OpenAI API key, and Telegram bot token.
• Voice message support requires an AWS S3 bucket.
• Configure TELEGRAM_TOKEN, OPENAI_API_KEY, and VOICE_MESSAGES_BUCKET in .chalice/config.json.
• Set Telegram webhook to the AWS Lambda Function URL.

Highlighted Details

• Supports new ChatGPT API.
• Includes voice message processing via S3.
• Renders responses with Markdown support.
• Future features include decoupled token refresh and improved performance.

Maintenance & Community

The project is maintained by franalgaba. There are no explicit mentions of community channels or extensive contributor lists in the README.

Licensing & Compatibility

The README does not specify a license. This may pose a restriction for commercial use or integration into closed-source projects.

Limitations & Caveats

The project is still under development with several features marked as "Coming soon," including enhanced error handling and performance improvements. The lack of a specified license is a significant caveat for adoption.