DeveloperWeek Management 2024 + AI DevSummit 2024 (+ DW Europe/LATAM 2024)

Blaize Stewart, Xebia, Architect

This session presents a demo-heavy exploration into application architecture and design patterns that leverage Large Language Models (LLMs), transforming application design, development, and deployment. This session showcases practical knowledge through demonstrations, guiding attendees through the forefront of AI application in software architecture. The session encourages audience participation with the content through a webpage that demos the content live.

The session begins by showing the foundational technique of leveraging LLMs through direct invocation. This part focuses on the art of prompt engineering, crucial for tailoring LLM responses to the nuanced needs of applications, ensuring precision and relevance.

Following this, the session talks about bridging natural language queries into structured queries. This demonstrates how to enable powerful searches across both structured and semi-structured data repositories, using LLMs to interpret and translate human queries into actionable database commands.

Next, the session looks at the LLMs and vector databases and how these work. It highlights how vector databases, when used alongside LLMs, allow for nuanced searches that go beyond keyword matching, offering a more intuitive and context-aware search experience.

The final part of the session looks at how LLMs work with other AI models. This shows how layering AI technologies to achieve a depth of interaction and functionality previously unattainable with single-model approaches, building applications that are richer and more engaging.