Building Scalable GenAI Apps Using Semantic Kernel and .NET Aspire
summary
Shows how Semantic Kernel plus .NET Aspire actually pieces together a production GenAI e‑shop: Azure OpenAI chat and embeddings, Postgres for products, Qdrant as the vector store, OpenTelemetry tracing, and a runnable sample on GitHub. Describes registering the kernel, creating embeddings on insert, doing semantic search + RAG, and orchestrating concurrent, sequential and group chat agents (example uses four agents: language, review, sentiment, summarize). Demo runs end‑to‑end and the sample code is available to clone and run.
AI-written summary · about
chapters (21)
- 0:00Introduction
- 0:49What is Semantic Kernel
- 3:17Semantic Kernel components
- 6:30Plugins and functions
- 8:37Semantic Kernel agent framework
- 10:23Agent orchestration types
- 15:21Demo setup with .NET Aspire
- 17:50Registering Semantic Kernel
- 24:11Vector database integration
- 28:59Implementing semantic search
- 32:45Agent setup in reviews microservice
- 37:20Agent orchestration services
- 43:27Exposing agents via A2A
- 46:43Consuming A2A agents
- 51:26Integrating MCP
- 55:27Q&A
- 1:01:53Comparison with Agent Framework
- 1:04:02Vector database recommendations
- 1:06:09Prompt engineering
- 1:08:56Aspire integration
- 1:11:48Closing remarks
related talks
01h 02mDevelop AI agents with Semantic Kernel
33mHow to enhance your own AI services using Semantic Kernel
01h 00mBuilding your own AI Agent using Semantic Kernel
47mAI Orchestration with Semantic Kernel
46mBuilding AI solutions with Semantic Kernel
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!
56mDeveloping AI Applications with SQL AI: Ground to Cloud to Fabric
50mBuilding AI ready applications