AI Orchestration with Semantic Kernel
summary
Semantic Kernel is an open‑source SDK that wires OpenAI, Azure OpenAI and Hugging Face into Java, Python and C# apps via a central kernel that routes calls to plugins (prompts, DB calls, functions). Demo shows domain‑aware translation using dynamic key/value overrides for batches (example scale: tens to hundreds of thousands of domain entries), a RAG over hundreds of anonymized resumes returning top three results, and object mappers to convert custom objects to/from strings. Works but has limits: Java SDK is feature‑behind, connectors aren’t provided out of the box and there is no embedding support built in.
AI-written summary · about
chapters (13)
- 0:00AI orchestration needs
- 6:50Why Semantic Kernel essential
- 11:31Semantic Kernel concepts
- 16:37SDK features and limits
- 18:40Kernel and services setup
- 20:47Prompts and plugins
- 23:42Automatic plugin invocation
- 25:34Custom objects in plugins
- 29:16Real-world use cases
- 35:27RAG with vector databases
- 37:23Structured data integration
- 40:41Hidden LLM use cases
- 45:38Resources and closing
related talks
33mHow to enhance your own AI services using Semantic Kernel
59mOrchestrate your AI with Semantic Kernel
46mBuilding AI solutions with Semantic Kernel
01h 02mDevelop AI agents with Semantic Kernel
01h 12mBuilding Scalable GenAI Apps Using Semantic Kernel and .NET Aspire
53mUnleash the power of AI: Automate tasks with OpenAI and Semantic Kernel
01h 00mBuilding your own AI Agent using Semantic Kernel
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!