Building and Evaluating RAG Pipelines
Key Takeaways:- Learn how to build a chatbot and RAG pipeline in Python.
- Discover techniques for evaluating the quality of chatbot responses.
- Explore a real-world use case of a New York Stock Exchange AI chatbot.
Description
Retrieval-Augmented Generation (RAG) pipelines are essential for building intelligent chatbots that can provide accurate, context-rich responses. Turning this concept into a working application requires hands-on experience with tools, techniques, and evaluation methods. In this session, you’ll bring it all together by building a real-world AI chatbot designed to answer questions about the New York Stock Exchange.
In this session, Abi Aryan, Founder at Abide AI, will walk you through how to build a RAG-powered chatbot using Python. You’ll learn how to construct the RAG pipeline, evaluate response quality, and apply it to real-world use cases. This session is ideal for AI engineers who want to deepen their RAG skills with a practical, high-value application.
Presenter Bio
Abi founded and runs the AI-assisted content creation platform Abide. She has a decade of experience as a machine learning scientist and engineer across e-commerce, insurance, and media. Abi is the author of the forthcoming book "LLMOps: Managing Large Language Models in Production".