Join us for a hands-on workshop showcasing the latest Azure SQL innovations to supercharge your applications. Learn how to harness generative AI alongside Azure SQL Database to elevate your data strategies with AI concepts like language models, prompt engineering, Retrieval Augmented Generation (RAG) and streamline with Microsoft Copilot. Whether you're a developer, architect, or IT professional, this workshop is your ticket to mastering SQL and AI to stay ahead in the data-driven landscape.

JoinMicrosoft’s product team for a hands-on lab where you'll design and deploy anAI-powered application using SQL Database in Microsoft Fabric. This sessiondives into HTAP capabilities, enabling seamless transactional and analyticalprocessing. You'll provision a SaaS-native SQL Database, use Copilot togenerate schema and queries, and implement advanced patterns like RAG withvector search. Walk away with practical skills and a working solution you canapply immediately.

Looking to add on-device AI to your apps? Not sure how to get started? Join our lab to learn how to integrate local AI capabilities into your Windows apps using Windows AI APIs. Discover how to implement Semantic Search and Retrieval-Augmented Generation (RAG) to power intelligent information retrieval, and use Phi Silica for on-device text processing. This lab will walk you through key APIs, and best practices to build on-device AI solutions for Copilot+ PCs. Developers of all levels welcome.

Whether you're building a chat application, a RAG system, or other AI tools, monitoring remains crucial. We'll show you how Datadog's comprehensive Azure monitoring can help you:

• Get started with PostgresSQL on Azure • Track PostgreSQL performance metrics that matter for GenAI workloads • Create dashboards and alerts that provide meaningful insights

In this talk, I'll cover the challenges of productionizing RAG in big tech vs startup: Latency/Throughput; Achieving High-Precision; Responsible AI; Grounding; Inferencing Cost

Python shines in RAG (Retrieval-Augmented Generation) systems due to its efficiency in orchestrating various processes and its extensive libraries, such as LangChain and Hugging Face Transformers. The building blocks for RAG include data extraction and preprocessing, transforming data into vectors via embedding models, and using vector databases for retrieval. Python excels in setting up data pipelines for indexing, retrieval, and generation, integrating different components, and ensuring low-latency, high-efficiency real-time processing. Real-world applications of RAG systems showcase Python's benefits and challenges in implementation, demonstrating its versatility and robustness in managing complex data flows and interactions.

Introduce LangGraph; Demo notebook of a RAG agent built w/ LangGraph; Demo some upcoming products from LangChain

Every company has a soup of documentation, tickets, Slack messages, powered rag to enable teams and chew through thorny mixtures of internal documentation and knowledge at company scale!

Foundations of LLMs and Python Basics; Understanding Natural Language Processing; Transformers and Attention; LLM Development: Fine-tuning and Prompt Engineering; Retrieval-Augmented Generation (RAG); Introduction to LLM Agents; Advanced Topics for Production LLM Application