Bridge the chasm between your ML and app devs with Semantic Kernel
summary
Semantic Kernel reaches v1.0 in Python C# Java and claims a stable cross-language asset model so ML teams build plugins, planners, and agents that app teams deploy without refactoring; the .NET kernel reports 1.1M .NET downloads. Demos show plugins invoking OpenAPI-backed light and image services, RAG with embeddings cached into Weaviate vector DB to speed retrieval, and automatic code execution via dynamic sessions/code execution to synthesize and run Python plans; enterprise hooks for safety, monitoring, and compliance are implemented and used in real Fujitsu and Accenture deployments.
AI-written summary · about
chapters (8)
- 0:00Semantic Kernel's mission
- 3:04AI researchers vs app devs
- 7:17Python & Java SDK v1.0
- 16:34Fujitsu's Composite AI system
- 28:46Demo: .NET with AI planning
- 33:03Enterprise safety features
- 34:10Accenture's AI assistant
- 40:19Call to action
related talks
46mBuilding AI solutions with Semantic Kernel
36mSemantic Kernel: the magical way of integrating LLMs into you
33mHow to enhance your own AI services using Semantic Kernel
01h 02mDevelop AI agents with Semantic Kernel
47mAI Orchestration with Semantic Kernel
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!
39mAI app 101: Starting from scratch with Semantic Kernel
53mUnleash the power of AI: Automate tasks with OpenAI and Semantic Kernel