In the short time that large language models have gone mainstream, we’ve started to see several patterns that AI researchers and developers have used to build their products. These include things like prompt engineering, prompt templating, chain of thought, vectorized memory and embeddings, and more. They’ve enabled new forms of natural language-based apps and have truly opened people’s imagination to what is possible with AI.
This presentation will cover a few of these recipes and how to build them using the Semantic Kernel, Microsoft’s latest open-source framework for developing AI and large language model applications. The Semantic Kernel incorporates the design patterns from the latest in AI research, and provides a multilingual SDK that developers can use to empower their apps with recursive reasoning, contextual memory, semantic indexing, planning, retrieval-augmented generation, and more. Come cook with us!