▶ Watch ↗AI Engineer World's Fair 20241:57:58
Build, Evaluate and Deploy a RAG-based retail copilot with Azure AI
Read the full talk →Key ideas
Scroll to read ↓Follow a retail RAG backend from product retrieval and customer lookup through prompt assembly, deployment and an evaluation that catches a convincingly invented product.
- What information does a retail chatbot need?0:00 ↗
- A tent recommendation, then a purchase-history question7:07 ↗
- Two retrieval paths meet in one prompt10:55 ↗
- Launch the lab, authenticate and inspect the data16:22 ↗
- What a flow owns40:13 ↗
- Prompt flow, application orchestration and the playground49:48 ↗
- Connections, persistence and search quality1:04:31 ↗
- Customer context is not customer authorization1:17:25 ↗
- From lookup results to a rendered prompt1:26:51 ↗
- Run locally, package the flow and understand its limits1:33:50 ↗
- A fluent answer can still invent a product1:41:20 ↗
- Use failures to change the system1:49:33 ↗
- Uploaded PDFs need a retrieval lifetime1:52:02 ↗