RAG Architecture | Scalable Architecture for LLMs

This video covers how to create a scalable architecture for LLMs using RAG (Retrieval Augmented Generation)
📌 Related Links
================
🔗 AI Primer Playlist - • AI Primer
⏱ Chapter Timestamps
====================
00:00 - Intro
00:05 - Agenda
00:36 - What is RAG?
02:12 - RAG Architecture
06:20 - Types of RAG Architectures
06:27 - Case Study: RAG in Document Search
08:27 - Case Study: RAG in AI Assistant for Chat Support (Food Delivery)
11:15 - Pros and Cons of RAG
12:44 - Trivia Question!
13:28 - Summary
Join this channel by contributing to the community:
/ @techprimers
📌 Related Playlist
================
🔗 AI Primer Playlist - • AI Primer
🔗Spring Boot Primer - • Spring Boot Primer
🔗Spring Cloud Primer - • Spring Cloud Primer
🔗Spring Microservices Primer - • Spring Microservices P...
🔗Spring JPA Primer - • Spring JPA Primer
🔗Java 8 Streams - • Java 8 Streams
🔗Spring Security Primer - • Spring Security Primer
💪 Join TechPrimers Slack Community: bit.ly/JoinTechPrimers
📟 Telegram: t.me/TechPrimers
🧮 TechPrimer HindSight (Blog): / techprimers
☁️ Website: techprimers.com
💪 Slack Community: techprimers.slack.com
🐦 Twitter: / techprimers
📱 Facebook: TechPrimers
💻 GitHub: github.com/TechPrimers or techprimers.github.io/
🎬 Video Editing: FCP
---------------------------------------------------------------
🔥 Disclaimer/Policy:
The content/views/opinions posted here are solely mine and the code samples created by me are open sourced.
You are free to use the code samples in Github after forking and you can modify it for your own use.
All the videos posted here are copyrighted. You cannot re-distribute videos on this channel in other channels or platforms.
#RAG #AIPrimer #Scale

[@ravideviceregunta5794]

The Best RAG architecture video ever seen…. Lot of people are complicate the concept a lot…
Could you do another video with the how prompt is compared with embeddings and measured accurate results…

[@TechPrimers]

Sure ravi. Will do

[@ramkarlapudi662]

Option 4

[@ravi1341975]

Option 4: Enhancing search results with relevant context

[@TechPrimers]

Spot on! Ravi!

[@abhijitprusty]

What is required to be a prompt engineer , it would be really nice if you could share some info. Once again, great to see your vides again

[@TechPrimers]

Sure Abhijit. It needs a mix of datascience and AI knowledge. Take a look at this datasciencedojo.com/blog/prompt-engineer/#:~:text=5%20essential%20skills%20for%20becoming%20a%20prompt%20engineer,knowledge%20...%205%205.%20Data%20analysis%20experience%20. Glad to be back😀

[@java-aws-techie]

Option 3 - Translating text between languages

[@TechPrimers]

Unfortunately no. Read through the options again. Clue lies in the texts itself 😁

[@java-aws-techie]

Got it - option 4: Enhancing search results with relevant context

[@blasttrash]

I think Option - 2 coz he used that in example-2 earlier.

[@TechPrimers]

Actually its option 4, since RAG helps in both enhancing search results (by the LLM) and with relevant Context (by the Retrieval mechanism).

[@amithraju830]

Very difficult to understand need more simplification

[@TechPrimers]

Sure Amith. When we get to handson part this will get better

[@sayanstrsc.7272]

🙏 Please remove that "thang thang" bell sound on subscribe request! Please remove that 🙏 Not useful, rather annoying, doesn't suit this channel or the kind of viewers of this channel!

[@TechPrimers]

done buddy. changed in all the new videos :)