Workshop: Fundamental of Context-Aware LLM-Based Chatbot Development
Workshop 1 - Prompt engineering, LLM Invocation using LangChain
Rapid development of AI technology has opened more applications of how we can introduce AI into processes
and building of our application. This workshop will focus on building the foundational skills needed to understand and build LLM products. This includes the best practices of prompt engineering, hands on Azure portal and introduction to Langchain framework. In addition, participants will gain practical and actionable insights to start crafting prompts that effectively harness the power of LLM.
This interactive session is the fundamental session to start experimenting with Microsoft Azure OpenAI API.
Workshop 2- Building Context-Aware Chatbots with Retrieval-Augmented Generation and Vector Stores
Take your chatbot development skills to the next level by exploring Retrieval Augmented Generation (RAG): a game changing approach for building smarter, context-aware chatbots. While traditional chatbots rely on preprogrammed responses or fine-tuned models, RAG integrates real-time retrieval of external knowledge to
handle complex queries dynamically in a cost-effective manner.
In this workshop, you’ll learn the foundational concepts of RAG, how it compares to standard chatbot methods, and its practical applications. Additionally, I’ll guide you step-by step through key processes of building an RAG-powered chatbot, including:
• Data vectorization
• Constructing a vector store/database
• Leveraging LangChain components to build your own RAG-powered chatbot
Perfect for those ready to move beyond the basics of chatbot development, this workshop will equip you with the tools to create intelligent, adaptable chatbots.