The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
🩺 AI-Powered Skin Health Assistant
I built a platform that identifies six common skin conditions from a photo — and then goes a step further with a built-in medical assistant that can actually talk you through it, remembering context across the conversation instead of answering questions one-off.
The Workflow:
📸 Image Classification — a ResNet50 model, fine-tuned via transfer learning, identifies the skin condition from a user-submitted photo.
🧠 Conversational Memory — built with LangChain, the assistant remembers earlier parts of the conversation, so users can ask follow-ups ("what about treatment options?") without repeating context.
💬 Symptom & Treatment Guidance — the assistant provides informational guidance on symptoms and general treatment options based on the identified condition.
⚡ Full-Stack Build — React frontend for a smooth user experience, FastAPI backend handling model inference and chatbot logic.
Tech Stack: ResNet50 (Transfer Learning), LangChain, React, FastAPI, Python
⚠️ Built as an informational tool, not a diagnostic replacement — always intended to point users toward professional medical care, not substitute for it.
🎬 Watch the demo below.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
E-Commerce Intelligence & Predictive Analytics Platform
Stripe posted about their new currency conversion feature yesterday, and the UI they shared caught my eye. So I built it out with React and added some motion to it.
The trickiest part was the balance-limit feedback. Animating a transform inside Framer Motion's layout system caused the card to re-measure and jump. Fixed it by isolating the shake onto a wrapper outside the layout tree.
Also made sure the motion respects prefers-reduced-motion.
What happens when an AI assistant needs answers from more than one source?
One of the challenges with building useful AI assistants isn't just generating a response.
It's making sure the response is based on the right information at the right time.
For FLT, the assistant needed to work across multiple data domains while supporting both text and voice interactions.
Instead of relying on a single static knowledge source, we built the system around a Retrieval-Augmented Generation (RAG) pipeline.
The approach connected authenticated APIs, SQL and JSON data sources so the assistant could retrieve relevant information before generating its response.
We also integrated:
→ Vapi for voice and chat interactions
→ Twilio for calls and SMS
→ RAG for contextual retrieval
→ SQL & JSON sources for dynamic data
→ Secure authentication for personalized experiences
The result was a full-stack AI assistant capable of delivering contextual responses across both chat and voice.
The key takeaway:
An AI assistant becomes much more useful when it can retrieve the right context instead of relying only on what the model already knows.
ai
rag
That's where the architecture behind the AI becomes just as important as the AI itself.
