Play 88
Visual Product Search
High✅ Ready
Image-based product discovery with visual similarity and virtual try-on.
Image-based product discovery combining reverse image search, visual similarity matching, style recommendations, and virtual try-on capabilities for fashion, furniture, and home decor retailers. AI Vision extracts visual features, OpenAI generates style descriptions and recommendations, AI Search indexes product embeddings, Container Apps serve the search API, and Cosmos DB stores product catalog and user preferences.
Architecture Pattern
Visual search pipeline: image upload - feature extraction - similarity matching - style recommendation - virtual try-on - product results
Azure Services
Azure AI VisionAzure OpenAIAzure AI SearchAzure Container AppsAzure Cosmos DB
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Visual Search Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (211 lines), evaluate (128 lines), tune (242 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + AI Search inputs + envFile
TuneKit (AI Config)
- config/openai.json - style description and recommendation prompts
- config/vision.json - similarity thresholds, catalog refresh, rendering quality
- config/guardrails.json - content moderation, result diversity thresholds
- evaluation/eval.py - Search relevance >85%, Try-on quality >80%
Tuning Parameters
Visual similarity thresholdStyle recommendation depthProduct catalog refresh rateTry-on rendering qualitySearch result diversity
Estimated Cost
Dev/Test
$80-200/mo
Production
$2K-8K/mo