How avinandan-mukherjee/localhost---portfolio-generator works
Project type and purpose
• This is a full-stack Flask web application (“LocalHost – AI Portfolio Generator”).
• Purpose: Accept user data via a form, call Google Gemini AI to generate a personalized portfolio site (HTML/CSS/JS), provide live preview, and allow download as a ZIP.
File structure
• Top-level Python modules:
• main.py – Flask app entry point, routes, AI orchestration
• input_form.py – WTForms definitions for user input
• Static assets (“static/”):
• inputstyle.css, mystyle.css, myscript.js – styling and behavior for the input & preview pages
• codes/ – dynamically generated portfolio output (images/, index.html, style.css, script.js)
• Templates (“templates/”):
• data.html – form page
• generated.html – preview/download UI
• Config/deployment:
• requirements.txt, .gitignore, Procfile, vercel.json
README for additional insights
• Architecture described verbally: Flask back end + Jinja2 templates + static preview + Google Gemini API integration.
• Key features: live preview toggle, download ZIP, theme customization.
Final recommendations
• Essential components—don’t omit the code-generation folder as it is central to the flow.
• Data flow end-to-end: user fills form → AI generates code → preview served → ZIP download.