DEV Community: NOSTRA

the Weekend Challenge: Passion Edition-(Passion-Roast)

NOSTRA — Mon, 13 Jul 2026 00:11:56 +0000

This is a submission for Weekend Challenge: Passion Edition

What I Built

Passion Roast is an AI "Passion Judge" that looks at a photo of your fan setup, collection, or hobby corner — plus the name of whatever you're obsessed with — and roasts you for it, scores your devotion out of 100, and hands you a mock diploma for your dedication.

The goal was simple: capture the universal feeling of being a little too into something you love, and let an AI genuinely react to real, specific details in your photo instead of giving generic responses.

Demo

🔗 Live app: https://passion-roast-production.up.railway.app
🎥 Demo video / GIF: <link here>

Try it with a photo of anything you're passionate about — a jersey collection, a gaming setup, houseplants, vinyl records, whatever. Each roast is generated fresh from what's actually in the picture.

Code

https://github.com/NOVA-X-Code/passion-roast

How I Built It

Backend: Node.js + Express, with Multer handling in-memory image uploads (no files ever touch disk).
Google AI (Gemini API): the entire app is built around a single multimodal call — the uploaded photo (as inlineData) and the declared passion are sent together to Gemini with a system prompt defining "The Passion Judge" persona. Gemini is instructed to return strict JSON (passion score, mock diploma title, roast, verdict), which the backend parses and validates before sending it to the frontend.
Frontend: vanilla HTML/CSS/JS with drag-and-drop upload and a shareable-style result card — no frameworks, no build step.

I deliberately kept the stack to a single external API. Rather than chaining multiple services, I focused on getting real value out of Gemini's multimodal reasoning: the roast has to reference actual details Gemini sees in the image, not just repeat the passion name back with generic flattery/insults.

Prize Categories

Best Use of Google AI

weekendchallenge

✧ 𝐍𝐎𝐒𝐓𝐑𝐀 ✧ 🚀 Building the Next Technological Era✨

NOSTRA — Fri, 10 Jul 2026 21:51:11 +0000

Welcome to ✧━━ 𝐍𝐎𝐒𝐓𝐑𝐀 ━━✧a technology Startup and Dev COmmunity driven by innovation, engineering, and research.

We are building the next generation of technologies across Software Engineering, Artificial Intelligence, Electronics, Embedded Systems, Cybersecurity, Cloud Computing, and Advanced Research.

Our mission is to engineer scalable, high-impact solutions that bridge software and hardware, transforming bold ideas into technologies that improve lives and shape the future.

We believe the world needs a new generation of innovators. Africa possesses extraordinary talent, creativity, and potential to contribute to global technological progress. At NOSTRA, we are committed to helping unlock that potential by building world-class technologies from Africa, for the world.

Innovation begins with an idea. Great technology begins with engineering.

━━━━━━━━━━━━━━━━━━

🌍 Join the NOSTRA Community

💬 Discord Community
https://discord.gg/xGAGs69UHj

📢 WhatsApp Official Channel
https://whatsapp.com/channel/0029Vb8ZJnsAYlUHo1uA6W0y

👥 WhatsApp Community
https://chat.whatsapp.com/LUkXjJNfWrT8Fz7akxosH0

👥 Facebook page
https://www.facebook.com/share/1BRrEoDWzQ/

Twitter
https://x.com/nostra237
━━━━━━━━━━━━━━━━━━

🚀 Together, let's engineer the technologies of tomorrow.

🐍 Build a Telegram Bot in 24 Hours: Complete Python Guide

NOSTRA — Wed, 08 Jul 2026 22:48:49 +0000

Ever wanted to build a Telegram bot but didn't know where to start?

After building 50+ bots for clients, I've distilled everything into a single, practical guide. No fluff—just code that works.
🎯 What You'll Build

A complete Telegram bot for video streaming with:

Multi-admin video upload

Smart search with filters

Role-based access (User, Admin, Owner)

Production-ready deployment

💻 Let's Start Coding
1. Setting Up Your Project

# Create project structure
mkdir my_telegram_bot
cd my_telegram_bot

# Create virtual environment
python -m venv venv
source venv/bin/activate  # Linux/Mac
# or
venv\Scripts\activate  # Windows

# Install dependencies
pip install python-telegram-bot==20.3 supabase python-dotenv

2. Your First Bot
python

# bot.py
import os
import logging
from telegram import Update
from telegram.ext import Application, CommandHandler, ContextTypes
from dotenv import load_dotenv

load_dotenv()
logging.basicConfig(level=logging.INFO)

async def start(update: Update, context: ContextTypes.DEFAULT_TYPE):
    await update.message.reply_text("👋 Hello! I'm your Telegram bot!")

def main():
    token = os.getenv('TELEGRAM_TOKEN')
    app = Application.builder().token(token).build()
    app.add_handler(CommandHandler("start", start))
    app.run_polling()

if __name__ == "__main__":
    main()

3. Add Async Commands
python

async def search(update: Update, context: ContextTypes.DEFAULT_TYPE):
    query = ' '.join(context.args)
    if not query:
        await update.message.reply_text("Usage: /search <keyword>")
        return

    # Simulate async database search
    await asyncio.sleep(0.5)

    await update.message.reply_text(f"🔍 Searching for: {query}")

🔐 Security Best Practices
python

# Rate limiting middleware
class RateLimiter:
    def __init__(self, max_requests: int = 30, window: int = 60):
        self.max_requests = max_requests
        self.window = window
        self.requests = {}

    async def is_allowed(self, user_id: int) -> bool:
        now = time.time()
        if user_id in self.requests:
            self.requests[user_id] = [t for t in self.requests[user_id] if now - t < self.window]
        if len(self.requests.get(user_id, [])) >= self.max_requests:
            return False
        self.requests.setdefault(user_id, []).append(now)
        return True

🗄️ Database Schema
sql

-- Users table
CREATE TABLE users (
    id BIGSERIAL PRIMARY KEY,
    user_id BIGINT UNIQUE NOT NULL,
    username VARCHAR(255),
    created_at TIMESTAMP DEFAULT NOW()
);

-- Videos table
CREATE TABLE videos (
    id BIGSERIAL PRIMARY KEY,
    file_id VARCHAR(255) NOT NULL,
    caption TEXT,
    tags TEXT[] DEFAULT '{}',
    owner_id BIGINT REFERENCES users(user_id),
    views INTEGER DEFAULT 0,
    upload_date TIMESTAMP DEFAULT NOW()
);

🚀 Deployment on Render (Free)
yaml

# render.yaml
services:
  - type: web
    name: telegram-bot
    runtime: python
    buildCommand: pip install -r requirements.txt
    startCommand: python -m src.bot
    envVars:
      - key: TELEGRAM_TOKEN
        sync: false
      - key: SUPABASE_URL
        sync: false
      - key: SUPABASE_KEY
        sync: false

📚 Go Deeper

This tutorial covers the basics. If you want to build a complete production-ready bot with:

✅ 8 chapters of step-by-step content
✅ Complete source code on GitHub
✅ Production-ready deployment
✅ 1 formats: PDF
✅ ENGLISH AND FRENCH VERSION
✅ Lifetime updates

📖 Get the Full Course

"Python Bot Mastery" – Build a Telegram bot from scratch in 24 hours.

🔥 Launch price: $10 (regular $14.99 – 33% off)

👉 Get your copy now

What would you build with a Telegram bot? Let me know in the comments! 👇