Introduction to RAG Applications: Building Conversational AI for Domain-specific Search

This beginner-friendly workshop introduces participants to the fundamentals of Retrieval-Augmented Generation (RAG) applications. Using a pre-configured Docker environment featuring Python, Elasticsearch for vector storage, and OpenAI as the LLM, attendees will learn how to build a RAG-powered conversational portal. Throughout the session, participants will create a RAG application to consume and query a sample dataset of Washington State regulation documents. Replace these sample documents with your own PDF files, and you’ll interact with your data in no time! By the end, attendees will be able to have a full survey of the components, technologies, and vocabulary necessary to make your own RAG application. A fully functional chatbot capable of searching, retrieving, and explaining information through natural language conversations. A flexible codebase that can consume almost any PDF document and start working out of the box The workshop covers essential concepts of integrating LLMs with vector databases, building data pipelines to index PDF documents, and designing search experiences that enhance accessibility to complex information. No prior experience with RAG is required, making this workshop perfect for developers, data practitioners, and AI enthusiasts looking to understand and build practical applications surrounding a unique data set.

Some experience with the Python programming language is recommended.

Required Software:

• Docker Desktop or similar software to run Docker containers
• Access to a terminal on their laptop
• Git integrated on their laptop
• VSCode or a preferred IDE for Python
• Justin will be running the workshop in OSX, but will be able to provide limited support for Windows and Linux