Build your Telegram assistant with Antigravity 2.0 /IDE

Build Your Telegram Assistant Bot with Antigravity 2.0 /IDE - 5 Labs Series

English Summary below

This project is a step-by-step tutorial and example project for developing a Telegram bot (smart assistant). The project is divided into 5 independent executable Lab directories, demonstrating how to build a smart assistant integrating Google Gemini 3.5 Flash and Imagen 3 from scratch.

📂 Project Directory Structure (Lab Planning)

This project adopts an incremental approach, with each Lab being a complete and independently executable project:

📂 Lab 1: Basic Bot Framework Building Telegram bot connectivity, basic commands (/start and /help), and Echo message replies.

📂 Lab 2: AI Presentation Generator Connects to Gemini 3.5 Flash to generate structured outlines and uses python-pptx to automatically draw presentations (supports Light/Dark theme settings).

📂 Lab 3: AI Image Generator Connects to the Gemini Imagen 3 image generation model, providing the /draw [scale] <description> command, supporting various aspect ratios such as 1:1, 16:9, 9:16, 4:3, and 3:4.

📂 Lab 4: AI Image Editor Upload an image to the bot, which will enter a waiting state for instructions, calling on Gemini multimodal and Imagen 3 to collaboratively modify the original image and send it back.

📂 Lab 5: Personal Notebook (Final Version) Integrates a local SQLite database to store personal notes and implements /addnote and /notes. An inline keyboard at the bottom of the list allows for asynchronous, seamless deletion of individual notes. This Lab is the most complete and ultimate version.