Agreed, simpler is almost always better. The hard part is resisting the urge to over-engineer it.
RAG Is Simpler Than You Think
91–100 of 155 posts
Re: RAG Is Simpler Than You Think
#92I 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…
How long have "large scale RAG systems" really existed in the first place? I'm always surprised at this, given how new all this really is, relatively speaking.
Re: RAG Is Simpler Than You Think
#93I 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…
I worked on getting an address database into elasticsearch years ago when it was still using modified tf-idf. Customers wanted FTS where a lot of the queries would be something like "100 First Ave, NY" or "200 2nd St, MN". It was one of the most fun projects I've worked on in my career so far. I got a learn a lot about how US and international addresses worked, so many edge cases, and got to really understand how cus…
What's your opinion on nominatim? I find that it gives up quickly when there's one or two typos in an address. It nails your examples.
Re: RAG Is Simpler Than You Think
#94Earlier quoted context omitted.
I thought text search was always the first thing you try, then fuzzy search, then you go for RAG
I think Bitwarden implemented some vector search in their password search feature ... totally annoying it gives me back all kinds of stuff that I don't care. I want fuzzy search like 95% of time and then I might consider having additional list of things that can be suggested by vector search.
Bandcamp has had legendarily bad semantic search for as long as they've been around. It's often completely impossible to find an artist or album or song even when you type the exact name.
Re: RAG Is Simpler Than You Think
#95I 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…
Yes, and don’t forget, LLMs are very good at tagging, so it’s not even that painful to backfill the corpus.
Re: RAG Is Simpler Than You Think
#96[flagged]
Re: RAG Is Simpler Than You Think
#97More LLM-generated text about LLMs. Is anyone else actually finding it harder and harder to read LLM generated text? I find it quite tiring, my brain just does not want to get through it.
I'm Becoming AI-Blind: https://news.ycombinator.com/item?id=49386699
Re: RAG Is Simpler Than You Think
#98Earlier quoted context omitted.
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.
I thought this would be a useless search that brought up pictures of rags, but indeed, DDG delivers a full page of results about retrieval-augmented generation for the query "rag"
Re: RAG Is Simpler Than You Think
#99I believe embedding-based RAG, everybody is using, will end. As chips advance, you would use a big llm instead of word embedding for retrieval. It's much more accurate and extensive covering every topic. Still need ~2 years to be replaced.
How would you use a big LLM for retrieval?
Re: RAG Is Simpler Than You Think
#100[flagged]