Build RAG Apps in YAML - Recording from the Intel AI DevSummit

Szymon Dudycz, AI Developer held a workshop at the Intel AI DevSummit, on February 26, 2025 on how to Build RAG Apps in YAML.

The session addresses accuracy limitations of traditional vector-indexing RAG for large, dynamic private data. It will explore how to build quality RAG applications for end users with easy-to-use RAG templates that can be deployed easily via docker, with the index of your choice. You’ll learn to optimize RAG for the best balance of cost, accuracy, and latency. We’ll showcase a quick, secure RAG service setup (CPU+GPU or CPU) with pre-built YAML templates and automatic data updates, improving document understanding and performance. You will see how it works in practice, with real-world querying of sales and marketing documents and slide decks.

• 00:00 Introduction and Speaker Introduction
• 00:59 Overview of the Pathway Live Data Framework and AI Pipelines
• 03:18 The Pathway Live Data Framework's Slide Search Service
• 07:29 Architecture and Technical Details
• 12:41 Live Demo: Slide Search in Action
• 25:06 Customizing Pipelines with YAML
• 33:57 Q&A Session
• 40:48 Closing Remarks and Next Session Preview

Speaker Bio: From building the core of the Pathway Live Data Framework's AI engine to crafting high-performance Monte Carlo simulations at Credit Suisse, Szymon knows how to make complex systems work. He's the wizard behind the framework's YAML templates. He holds a PhD on approximation algorithms.