AI Shopping Assistant: Using metadata filtering with RAG

Video: AI Shopping Assistant - Built using LangGraph

Innovative solution involves a Chat based AI assistant designed to help customers find items, explain product details, and upsell relevant products. I’ll take you through our journey from problem identification to the development of a Minimum Viable Product (MVP) built with OpenAI GPT-4 and a vector-based self-querying retriever for accurate product recommendations. For this project we use Langraph agents and vector based RAG system that uses metadata filtering.