PyData NYC 2024

Make sure you clone the GitHub repo and complete the instructions at the README before joining: https://github.com/theam/rag-workshop-pydata-nyc-2024

Anyone building AI applications today is likely dappling with a diversity of technologies––and particularly RAG (Retrieval-Augmented Generation). This workshop offers a comprehensive introduction to building RAG applications, exploring the architecture and good design principles, while diving into hands-on examples with popular open-source AI & data engineering tools such as LangChain, ChromaDB, and embedding models. 

The workshop will cover building effective search pipelines, chaining multiple language models (LLMs) to enhance response quality, and the use of embeddings to improve search relevance. You'll learn about emerging concepts like correctness evaluation, as well as test automation for AI applications. Each module in the workshop will present hands-on examples such as creating pipelines and querying results, reviewing results for correctness, integrating embeddings, and setting up an LLM to evaluate another LLM for correctness. Participants will have the opportunity to tinker with constructing and evaluating RAG applications using best of breed open source & industry standard tools, and practical methods to start building RAG applications based on these concepts immediately.