Navigate Select ESC Close

How RAG Turns AI Chatbots Into Something Practical

2024-08-24 Science & Technology
119.1k
4.0k
122
bycloud
bycloud
229.0k subscribers

Unlock all features

FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.

Description

Check out ThinkBuddy using the code "BYCLOUD" in the link: https://thinkbuddy.ai/ltd to get your discount! my newsletter: https://mail.bycloud.ai/ Retrieval augmented generation, a current popular method to utilize LLMs to retrieve from a database instead of putting everything in a context window. But how does it work? Today I will walk through the most basic idea of RAG and the current meta of how RAG is used, and what it is composed of. My own RAG experiment on 1TB of PDFs: https://youtu.be/KL5Au8pKJ38 some papers [Web + RAG] https://arxiv.org/abs/2408.07611 [Vector + KG RAG] https://arxiv.org/abs/2408.04948 [RAG Survey] https://arxiv.org/abs/2404.10981 [Knowledge Graph for RAG] https://docs.llamaindex.ai/en/stable/examples/query_engine/knowledge_graph_rag_query_engine/ [LlamaIndex] https://www.llamaindex.ai/ [LlamaParse] https://docs.llamaindex.ai/en/stable/llama_cloud/llama_parse/ [HuggingFace] https://huggingface.co/models [Cohere Command R+] https://docs.cohere.com/docs/command-r-plus [Cohere Rerank] https://docs.cohere.com/docs/overview [Cohere Embedding Models] https://cohere.com/blog/introducing-embed-v3 [GraphRAG] https://github.com/microsoft/graphrag [RAGAS] https://github.com/explodinggradients/ragas This video is supported by the kind Patrons & YouTube Members: 🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Owen Ingraham, Tanaro, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford [Discord] https://discord.gg/NhJZGtH [Twitter] https://twitter.com/bycloudai [Patreon] https://www.patreon.com/bycloud [Music] massobeats - glisten [Profile & Banner Art] https://twitter.com/pygm7 [Video Editor] @Askejm

Top Comments (10)

@Laszer271 2024-08-26

LLMs are like cars, if it stands in the middle of the deep forest we can point at it and laugh at how it's stupid and how it's better to just walk through the forest. RAG and tools (as in tool-calling for llms) are the infrastructure comparable to roads. Many people don't realize that once the "car" gets on the proper "road", it is all of sudden very efficient at what it does. We don't faster cars (e.g. GPT-5), infrastructure is all we need right now.

58 2 replies
@bycloudAI 2024-08-24

Check out ThinkBuddy using the code "BYCLOUD" in the link: https://thinkbuddy.ai/ltd to get your discount!

46 2 replies
@kylebroflovski6382 2024-08-24

Long time no see bycloud

33 1 replies
@kocokan 2024-08-25

Describing all these AI news and papers for casual mortals takes significant efforts

33
@SperkSan 2024-08-25

Your thumbnail reminds me of The Code Report

31 2 replies
@TegraZero 2024-08-25

Video went from RAGs to Riches

22
@BunsDev 2024-12-22

Timestamps 00:04 - RAG enhances AI chatbots for practical use 01:20 - RAG process involves indexing, retrieval, and generation stages. 02:35 - Utilizing DALL-E to formulate coherent and contextually relevant responses. 03:53 - Using trainable embedding model for better document organization 05:13 - AI chatbots use input query rewriting and hybrid search for accurate information retrieval. 06:36 - RERank model uses threshold to filter out irrelevant information 07:55 - Think Buddy combines the strengths of multiple AI models for instant help. 09:11 - Get 30% off with limited code for first 50 sales

10
@GoetheNorris 2025-04-07

Interesting and well done video, despite trying hard to imitate fireship

1
@googletjanster2917 2025-05-10

fireship thumbnails going hard lol

0
@L2Anders83 2025-07-30

Major companies are seriously overselling the necessity for higher compute to get everything! When you really only want to understand a limited amount of information. This is great!

0

Unlock the Data Inside
Turn Videos into Knowledge

  • Get FREE 10/day: transcripts, summaries, chats
  • Chat with videos, export text & PDF
  • $1 free API credit for RAG, chatbots & research

Free forever plan • All features unlocked

App screenshot