LlamaIndex Webinar: Building LLM Apps for Production, Part 1 (co-hosted with Anyscale)

While setting up a naive RAG stack is straightforward, addressing a long tail of quality, evaluation and scalability challenges is essential for software engineers to render their applications production-ready.

​This multi-part workshop series will guide you through using LlamaIndex and Ray to implement reliable and scalable RAG.

​You'll learn how to build RAG and approach scalability challenges, design experiments to optimize key application components and utilize scalable workflows to quantitatively compare them.

Part 1:
- Learn about LlamaIndex + Ray, and how to setup a RAG stack with the two technologies

In the next lessons we'll dive into evals and optimization.

​Instructors:
Simon (co-founder/CTO, LlamaIndex)
​Adam (Technical Trainer, Anyscale)

[ShawhinTalebi]

This was an awesome session. Thanks for sharing!

[zachadolphe]

I keep getting an error of: "TypeError: cannot pickle '_thread.RLock' object". Do you know what might be causing this? It happens in the execution kernel for calling the map batches and ingesting data into the vector db.