Large Language Models, data & APIs: integrating generative AI power – with Python & .NET

Human language as a universal interface for software solutions – sounds exciting! In this session, Christian offers an introduction to the integration of generative AI and Large Language Models (LLMs) into your applications. Using Python and .NET APIs, he shows how to exploit the potential of LLMs for various use cases.
At the core of the integration are the attendee’s data, API, and document. We’ll cover architecture patterns like In-Context Learning, Retrieval-Augmented Generation (RAG), Reasoning & Acting (ReAct), and Agents. These techniques are crucial for the development of modern, AI-driven business applications.
For more complex requirements, you’ll see how to employ LangChain for Python and Semantic Kernel for .NET. These frameworks open up enhanced opportunities for text understanding and generation, especially concerning prolonged conversations.
Christian will also provide an overview of Cloud-based solutions, including Azure Open AI Service and Fermyon Serverless AI, focusing on the option to provide and utilize own LLMs based on GPT-4 or Llama2.
Come and join to experience a pragmatic approach to integrating generative AI into business applications!