AI Orchestration with Semantic Kernel
In the previous chapter, we covered the basics of generative AI and how large language models (LLMs) can be used to generate chat responses, text embeddings, and images. We also saw how prompt engineering can help with customizing the behavior of an LLM.
In many applications, these tools will be all you need to build and deploy an effective application. However, sometimes you need the ability to integrate different data sources into your application.
In this chapter, we’ll talk about AI orchestration and retrieval-augmented generation (RAG) and how they extend the capabilities of generative AI systems.
We’ll specifically be focusing on Semantic Kernel, Microsoft’s open source AI orchestration framework, and seeing how we can define simple functions that can work together to achieve complex results.
In this chapter, we’ll cover the following topics:
- Understanding RAG and AI orchestration
- Introducing...
