Скачать или смотреть Simplify AI development maximizing the power of local models and MCPs | ODFP973

This is one of many innovative Featured Partner sessions from Microsoft Build 2025. View more information from this partner at https://aka.ms/MSBuild25_Docker

Local LLM development is no longer a niche—it’s becoming a necessity. Developers are increasingly choosing to run models locally to gain better performance, reduce costs, and maintain data privacy. But despite the growing demand, the local AI development experience remains fragmented and complex. In this session, you’ll get a first look at how Docker is streamlining local AI workflow.
We’ll also explore Docker’s support for the Model Context Protocol (MCP)—a new standard that defines how appli

𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀:
Michael Irwin


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

ODFP973 | English (US) | AI, Copilot & Agents


#MSBuild, #AI

Chapters:
0:00 - Introduction to Docker Model Runner
00:00:55 - Challenges of Running Models with GPUs in Containers
00:02:41 - Accessing Models from Docker Hub
00:05:12 - Addressing Container Environment Issues
00:05:54 - .NET Application Integration with OpenAI API
00:07:41 - Application Demo for Product Feedback Analysis
00:10:14 - Introduction to MCP
00:13:45 - Configuration and integration of MCP with GitHub and Python ecosystems
00:14:45 - Introduction of MCP Catalog and Benefits of Containerization