AI-Powered Visual Product Search

Overview

Developed an image-based product search system for a major retail chain with 100K+ SKU catalog. Customers upload a product photo and instantly find matching items in stores. The solution uses a novel approach: LLM generates semantic descriptions from images, which are embedded and matched against the catalog via vector similarity search.

Achievements

Sub-second visual search across 100K+ products. Smart adaptive indexing automatically selects between incremental and full catalog rebuilds, keeping the index up to date with minimal downtime.

Responsibilities

• Designed AI pipeline: image → Gemini Vision description → text embedding → Vertex AI Matching Engine vector search (top-50, cosine ≥ 0.60)
• Implemented deterministic prompt engineering for consistent product descriptions optimized for embedding quality
• Built smart sync strategy with automatic incremental vs full rebuild selection based on change volume
• Developed role-based JWT auth (Owner/Admin/User) with domain restrictions
• Deployed with Docker Compose, Nginx, automated SSL

Technologies Used