Foundry IQ for Agentic Retrieval | Intro to enterprise RAG in Microsoft Foundry

Learn how Foundry IQ uses Knowledge Bases and Knowledge Sources to simplify Agentic Retrieval. Build enterprise-ready RAG in Microsoft Foundry. Here’s what you’ll learn: 🔥 📌 Beyond v1.0 RAG: Why standard retrieval architectures hit a wall when your data is scattered across SharePoint, SQL, Storage Accounts and other. 📌 Agentic Retrieval: How to let the LLM act as the "brain" to plan, decompose, and reflect on complex queries automatically. 📌 The "USB" Architecture: How to configure reusable Knowledge Bases that you can "plug" into multiple agents without writing redundant code. 📌 Real-Time Context: Using Remote Knowledge Sources like Web Search and SharePoint calls to fetch live data exactly when it’s needed. 📌 Live Walkthrough: A step-by-step guide to configuring the orchestration layer in Microsoft Foundry. 👉 Blog post: https://deployedinazure.com/foundry-i... ----- 0:00 Intro 1:10 Quick Demo 2:51 Classic V1 RAG limitations 6:56 Foundry IQ config in Microsoft Foundry 22:44 Foundry IQ in action 32:40 When to use Foundry IQ 36:04 Summary ----- Follow me 👉 🌐 Blog: https://deployedinazure.com 💻 GitHub: https://github.com/deployed-in-azure 🔗 LinkedIn:   / deployed-in-azure