Building Performant RAG Applications for Production • David Carlos Zachariae • GOTO 2024

This presentation was recorded at GOTO Copenhagen 2024. #GOTOcon #GOTOcph
https://gotocph.com

David Carlos Zachariae - Software Developer at Trifork

RESOURCES
https://github.com/arumie
  / david-carlos-zachariae  
https://dzach.dev

ABSTRACT
In today's rapidly evolving technological landscape, Large Language Models (LLMs) are transforming AI applications but often lack specific knowledge outside their training data. Enter Retrieval Augmented Generation (RAG), offering a compelling solution to bridge these knowledge gaps. Transitioning baseline RAG applications to production, however, present challenges that might prevent applications from exiting the prototyping stage.

Our presentation will explore how to develop production-ready RAG applications, highlighting the common challenges and advanced techniques needed to overcome them. Attendees will gain insights into ensuring flexibility, reliability, predictability, and scalability in their RAG pipelines, enabling them to handle diverse and complex tasks. Supplemented by a realistic use case and practical code examples, we will equip developers with a robust toolkit for building high-performance RAG applications. We will delve into the nuances of RAG, demonstrating its transformative potential and providing you with the knowledge to harness its full capabilities in your own applications. [...]

TIMECODES
00:00 Intro
00:50 Agenda
01:42 Why use RAG?
03:52 Performant RAG?
04:44 Use-case
05:18 First iteration: The simple case
07:27 Demo
09:48 Second iteration: Multiple categories of documentation
12:50 Demo
14:43 Third iteration: Unstructured documentation
17:50 Demo
19:56 Fourth iteration: Dynamic context & actions
24:22 Demo
29:15 Take-aways
31:33 Outro

Download slides and read the full abstract here:
https://gotocph.com/2024/sessions/3276

RECOMMENDED BOOKS
Bahaaldine Azarmi & Jeff Vestal • Vector Search for Practitioners with Elastic • https://amzn.to/3ZCGSfa
Madhusudhan Konda • Elasticsearch in Action • https://amzn.to/3P4sQ16
Huage Chen & Yazid Akadiri • Elastic Stack 8.x Cookbook • https://amzn.to/3DymaFW
Asjad Athick • Getting Started with Elastic Stack 8.0 • https://amzn.to/41Cu8YN

https://bsky.app/profile/gotocon.com
  / gotocon  
  / goto-  
  / goto_con  
  / gotoconferences  
#RetrievalAugmentedGeneration #RAG #RAGPipelines #ELSER #VectorSearch #ElasticPlayground #GenerativeCaching #VectorEmbedding #TodayInTech #DavidCarlosZachariae

CHANNEL MEMBERSHIP BONUS
Join this channel to get early access to videos & other perks:
   / @goto-  

Looking for a unique learning experience?
Attend the next GOTO conference near you! Get your ticket at https://gotopia.tech
Sign up for updates and specials at https://gotopia.tech/newsletter

SUBSCRIBE TO OUR CHANNEL - new videos posted almost daily.
https://www.youtube.com/user/GotoConf...