Advanced RAG tutorial with Llamaindex & OpenAI GPT: Sentence Window Retrieval vs Basic Chunking

preview_player
Показать описание
Correction: at 1:53, I said that an embedding is a x digit string. That is not correct, it should be a list of x numbers.

Why build your own retrieval augmented generation pipeline when OpenAI's custom GPTs can do it out of the box? Did you know that the OpenAI solutions, as of the making of this video, are not scalable to large knowledge bases? Also, having your own pipeline gives you a lot more control over the design which you will need if you are building an enterprise grade top-notch system.

In this tutorial, we will talk through a number of advanced techniques such as sentence window retrieval, hierarchical automerge retrieval, returning Top K results vs. greedy search, reranking etc.

We will also work through some code and do a real comparison between basic chunking vs. sentence retrieval strategies.
Рекомендации по теме
Комментарии
Автор

This is currently the best RAG tutorial on the internet.

mikestaub
Автор

As always, well prepared, easy to follow video that delivers a lot of information and value. Thank you!

nazihfattal
Автор

Your explanations and delivery is on point. Thank you for an excellent content and relaxed narration style.

MaliRasko
Автор

Great video with an awesome easy to follow explanation of RAG. Reminds of a recent Andrej Karpathy video.

sitedev
Автор

Wow, that’s a wonderful piece of advice from such a talented professional in the field. Thank you 😊

arjoai
Автор

Fascinating! Your approach to teaching and presenting is poetic. It is well organized, well explained, and well illustrated. Indeed, kudos to you. If I could, I would subscribe to your channel twice!

unclecode
Автор

clear effective explanations thank you

victorfeight
Автор

Great job explaining window and how vector store and doc store relate and where window lives. I’ve been trying to understand this aspect of llamaindex, and you made it very clear!

danielvalentine
Автор

Llama Index has new version 0.10 - will migrate your codes n learn same time.
Thanks for introducing Sentence Window Retrieval. Most basic straight-split and retrieve/chat doesnt produce much meanings on our docs.

ginisksam
Автор

Awesome video explained very clearly! Thanks a ton!
If I may ask, what tool do you use for those visual flows. Love it!

sivi
Автор

Really cool video! Is there an "ideal" or "recommended" value of window_size?

sayanbhattacharyya
Автор

Excellent video. Liked the workflow you showed in the beginning. What SW are you using to create this workflow?

Work_Pavan-muye
Автор

I'm a bit confused on the use case for re-ranking. Doesn't that defeat the purpose the top-k search in that we include all chunks, significantly increasing the number of tokens we use? Is the idea to do re-ranking with a smaller & cheaper LLM before sending the resultant top-K chunks to a more robust LLM?

peteredmonds
Автор

Seeing your explaination at around 09:30, it seems like we can only use K windows to serve as knowledge base to answer a prompt. What If the prompt asks information that is contained in more than K windows? Like if I have several documents containing each a bio of a person, and if the user asks to sort those 10 people by age... how can it figure it out? I guess we can use a big value for K, if the cosine similarity engine can take it... but I am guessing providing too much context to the LLM will cost a lot of money?

goonymiami
Автор

Small correction: embedding are not a 1536 digit number but of vector of size 1536

peteredmonds
Автор

Great video? Is the diagram anywhere to refeeence?

chiggly
Автор

it is 1784 in teahistory.txt and 1794 in chinahistory.txt so bit confusing
but anw great tutorial Thanks

jannessantoso