Memory and agentic RAG with Azure AI Search

Post Content

Check out our multi-agent RAG system with built-in memory, for more proactive knowledge retrieval and advanced query planning.

To learn more, please check out these resources:
* https://aka.ms/build25/plan/CreateAgenticAISolutions

𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀:
* Ben Ufuk Tezcan

𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻:
This is one of many sessions from the Microsoft Build 2025 event. View even more sessions on-demand and learn about Microsoft Build at https://build.microsoft.com

DEM529 | English (US) | AI, Copilot & Agents

#MSBuild

Chapters:
0:00 – Changes in Knowledge Interaction in Last Two Years
00:00:22 – Role of Large Language Models in Simplifying Interactions
00:00:53 – Exploring Future Capabilities and Customizations of LLMs
00:04:33 – Initialization of the travel assistant prompt
00:06:20 – Memory initializing and loading past conversations
00:08:13 – Integration of Memory in User Queries
00:08:25 – Demonstration of Interaction and Memory Implementation
00:12:33 – Instance Explanation of Product Advisor and Travel Assistance
00:13:15 – Examples of Queries Addressed to the AI System Read More Microsoft Developer