Clean Your Filthy RAGS! Optimizing, Accelerating, and Evaluating RAG Applications

Retrieval-Augmented Generation (RAG) applications are becoming essential for companies, combining AI with real-time data retrieval to enhance customer experiences. While Large Language Models (LLMs) handle general conversation well, they struggle with domain-specific, up-to-date information, often producing inaccurate or unhelpful responses. This workshop will empower participants with the necessary skills to optimize RAG applications using existing best practices. Justin will walk through integrating RAGAS, a framework designed to evaluate, monitor, and fine-tune the performance of RAG applications. Participants will use benchmarking tools to measure and improve data retrieval performance and explore semantic caching with Elasticsearch to reduce redundant LLM queries, speeding up response times in real-time applications. Attendees will receive a Docker container with a Python-based RAG application powered by OpenAI's LLM and Elasticsearch for vector storage. Attendees will leave with hands-on experience and a fully functional RAG application they can customize.

This workshop is ideal for developers, data engineers, and AI enthusiasts looking to deepen their understanding of RAG architecture and achieve measurable improvements. Familiarity with RAG infrastructure, Python, and Jupyter Notebooks is strongly recommended for participants to get the most out of the session.

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