Retail AI benchmark for choosing the economically right LLM by workflow
Zero-shot SKU onboarding for edge retail AI — single product photo → trained detector in <10 min via LLaVA extraction, BlenderProc2 domain randomization, YOLOv8n + EWC continual learning, and async FastAPI.
A synthetic-data retail AI agent prototype for product discovery, order support, and assistant workflow evaluation.
Semantic grocery search engine using ChromaDB + SentenceTransformers — find products by meaning not just keywords using cosine similarity HNSW indexing
Computer vision model to estimate customer age from photos. Uses fine-tuned ResNet50, achieves MAE 6.37 (<8 target). Enables personalized offers and age verification for alcohol sales.
Add a description, image, and links to the retail-ai topic page so that developers can more easily learn about it.
To associate your repository with the retail-ai topic, visit your repo's landing page and select "manage topics."