Site Icon Matthew Raynor
← Back to Services

Photography Store

E-commerce platform for fine art photography prints. Three collections of Hamptons landscape photography, museum-quality printing in multiple formats, gift cards, and promo codes. An AI shopping assistant understands what's in each photo — ask for 'sunset over the ocean' and it finds matches using vector search. A 'See in Room' tool lets customers preview prints on their own wall using ML-powered wall detection. Includes a self-hosted newsletter platform.

Project Overview

A complete e-commerce platform for fine art drone and seascape photography targeting the Hamptons luxury art market. Features an AI shopping assistant built with LangChain and Claude that can search photos semantically, manage carts, visualize prints on customer walls using depth estimation, and handle checkout through conversation.

The Challenge

Selling fine art photography online requires more than a product grid — customers need to discover art by mood and meaning, visualize how pieces look in their space, and feel confident about size and materials before purchasing.

The Solution

Built an AI shopping assistant with 14 tools that searches photos semantically using pgvector embeddings, manages carts, filters by color/mood/subject, checks gift card balances, and answers sizing questions. The 'See It In Room' feature uses MiDaS depth estimation + RANSAC plane-fitting to composite prints at correct scale on customer-uploaded wall photos.

Technology Stack

Backend
Django 5 Django REST Framework PostgreSQL pgvector Celery Redis
Frontend
Next.js 15 TypeScript Tailwind CSS
Ai
LangChain Claude API Claude Vision OpenAI Embeddings MiDaS Depth Estimation
Integrations
Stripe Checkout AWS S3 Resend Listmonk Sentry
Deployment
Railway Netlify

Key Features

AI shopping assistant with 14 tools — search, cart, checkout, wall visualization all through conversation

pgvector semantic search using OpenAI text-embedding-ada-002 for meaning-based photo discovery

Claude Vision auto-generates all photo metadata (descriptions, moods, colors, subjects)

'See It In Room': MiDaS depth estimation + RANSAC plane-fitting composites prints at correct scale

Stripe Checkout with gift card redemption and promotional codes

Self-hosted Listmonk newsletter with Amazon SES delivery

Custom privacy-friendly analytics — no cookies, no third-party tracking

Business Impact

Semantic photo discovery — customers find art by meaning, not just keywords

Realistic wall visualization reduces purchase hesitation for expensive prints

Conversational commerce handles the entire shopping experience through the AI assistant

Automated metadata generation eliminates manual photo tagging

Technical Achievements

MiDaS + RANSAC pipeline that accurately places prints on real walls

Semantic search that understands 'moody ocean sunset' or 'bright aerial beach'

Full conversational commerce — browse, add to cart, and check out without leaving the chat

Self-hosted newsletter replacing paid services like MailerLite

Technical Implementation

Photo embeddings generated with OpenAI text-embedding-ada-002, stored in PostgreSQL with pgvector for cosine similarity search. The AI assistant uses LangChain with Claude and 14 tools for a complete shopping experience. The 'See It In Room' feature uses MiDaS depth estimation to find walls in uploaded photos, then RANSAC plane-fitting to composite prints at physically accurate scale. Self-hosted Listmonk newsletter on Railway with Amazon SES for delivery and SNS for bounce/complaint handling.

Interested in This Project?

View the source code or see it in action