Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

RAG Is Simpler Than You Think

lighthousenewsletter.com

Post reply on HN
Print view View original

31–40 of 125 posts

Re: RAG Is Simpler Than You Think

#31

Post by simianwords »

imtringued wrote: post #26
simianwords wrote: post #17

OT but its interesting that none of the harnesses today use embeddings but just simple grep. I would not have predicted this

Ok? I'm not seeing how that is interesting, you're exclusively focusing on coding which requires precise substring locations. Google is basically almost entirely driven by embedding models now.

And why do you think coding didn’t benefit from embeddings? It was attempted many times and the industry gave up.

I find this interesting because practically no one is doing RAG on thier personal data which is something I wouldn’t have expected.

Re: RAG Is Simpler Than You Think

#32

Post by vaylian »

dotancohen wrote: post #25
Angostura wrote: post #6

I have a particular antipathy for articles too lazy to spell out acronyms on first use. So: https://en.wikipedia.org/wiki/Retrieval-augmented_generation

The audience for this piece is already very familiar with RAG. I don't want articles discussing e.g. OLED screens telling me what the acronym is - that would be a sign that the article is far below the level that I need.

A hyperlink to Wikipedia would have solved that issue.

Re: RAG Is Simpler Than You Think

#33

Post by kaon_2 »

usernametaken29 wrote: post #27

I worked on large scale RAG systems before and can say people vastly underestimate full text search and vastly overestimate embeddings. FTS is really easy, portable and scalable and gets you very far, the 80/20 rule applies. Embeddings appear to be nice and magic but when you really get into them you notice: semantic similarity isn’t as good as you think and certainly it won’t make everyone happy. You will inevitably…

Can you elaborate? We have technicians searching in different languages. Also our knowledge base is often in different languages. I just don't see how full text search can work? Maybe in a problem space like a wiki where people always know what to search for?

Re: RAG Is Simpler Than You Think

#34

Post by redsocksfan45 »

vaylian wrote: post #32
dotancohen wrote: post #25

Earlier quoted context omitted.

The audience for this piece is already very familiar with RAG. I don't want articles discussing e.g. OLED screens telling me what the acronym is - that would be a sign that the article is far below the level that I need.

A hyperlink to Wikipedia would have solved that issue.

[dead]

Re: RAG Is Simpler Than You Think

#35

Post by jon-wood »

kaon_2 wrote: post #33
usernametaken29 wrote: post #27

I worked on large scale RAG systems before and can say people vastly underestimate full text search and vastly overestimate embeddings. FTS is really easy, portable and scalable and gets you very far, the 80/20 rule applies. Embeddings appear to be nice and magic but when you really get into them you notice: semantic similarity isn’t as good as you think and certainly it won’t make everyone happy. You will inevitably…

Can you elaborate? We have technicians searching in different languages. Also our knowledge base is often in different languages. I just don't see how full text search can work? Maybe in a problem space like a wiki where people always know what to search for?

Instinctively this feels like a two phase problem - start with some machine translation into a single spoken language and index that, then when people are querying do the same thing. When returning search results show them in the original language.

Re: RAG Is Simpler Than You Think

#36

Post by Lorean1 »

vaylian wrote: post #32
dotancohen wrote: post #25

Earlier quoted context omitted.

The audience for this piece is already very familiar with RAG. I don't want articles discussing e.g. OLED screens telling me what the acronym is - that would be a sign that the article is far below the level that I need.

A hyperlink to Wikipedia would have solved that issue.

Maybe if a person can't even google RAG they are not the intended audience of that article.

Re: RAG Is Simpler Than You Think

#38

Post by KaseyKim »

brabel wrote: post #11
nilirl wrote: post #4

Maybe I'm old but where exactly are the "dragons"? How is RAG any different from the search systems we've been building before LLMs? Is it the sudden need for everyone to design a search API and engine that's driven this trend? If so, I'd like to see more design patterns around existing search problems: - Correcting or backtracking based on feedback. - Measuring relevance. - Comparison with task-based pre-written que…

The whole embedding thing which converts “tokens” to vectors, which you then store in a vector database so that you can later query by vector distance, seems to be LLM specific technology, no? As far as I know the vectors look a lot like the weights in a LLM itself which is why the vector search also works with some level of intelligence.

right, it is the foundation of machine learning.

Re: RAG Is Simpler Than You Think

#39

Post by jrochkind1 »

bob1029 wrote: post #15

Agentic query rewrite on top of good old fashioned Lucene is the end game. This is effectively providing a lot of the same magic you get with the semantic approach. Allowing the agent to query the document store iteratively is where the capabilities become unbounded. Embeddings and semantic search add non determinism on top of non determinism. This seems fundamentally cursed. Lexical is much easier to control, iterat…

An LLM wrote this comment, no? I'm curious your motivation for having an LLM write such a short comment instead of writing it yourself?
Post reply on HN