Ifihan/pycon-nigeria-2025

Demo for my session at PyCon Nigeria '25 # Python + Gemini: Multimodal Superpowers for Your Apps Interactive codelab for PyCon Nigeria '25 session on building multimodal applications with Python and Google Gemini. ## Overview This project guides you through building a multimodal web application that can analyze images using Google's Gemini AI. You'll start with a simple command-line Python script and evolve it into a fully interactive web application. ## What You'll Build - A Python script that analyzes images with text prompts - A web app where users can upload images, ask questions, and see Gemini's responses ## Prerequisites - Python 3.8+ - A Google Gemini API Key from Google AI Studio - A code editor (VS Code recommended) ## Getting Started Simply open `main.html` in your web browser to access the interactive codelab. The tutorial will guide you through: 1. Setting up your Python environment 2. Installing required packages 3. Building a command-line prototype 4. Creating a web application with Flask 5. Deploying your multimodal app ## Time to Complete 20-25 minutes ## Built With - Python - Google Gemini API - Flask - HTML/CSS/JavaScript ## Author Built by Ifihan for a PyCon Nigeria 2025 session. ## Contributing Contributions are welcome! Feel free to submit issues or pull requests.