RAG Is Simpler Than You Think
lighthousenewsletter.com
RAG Is Simpler Than You Think
1–10 of 125 posts
Re: RAG Is Simpler Than You Think
#2There have been many blogs like this over the last years.
Yes, embeddings are computationally heavy, but they are not at all complicated and they provide a lot of benefit.
90% of "document" based RAG projects should view semantic search with embeddings as their primary method.
It's very powerful and so easy to implement that you could try it out and discover whether performance would be an issue rather than trying to anticipate it.
Re: RAG Is Simpler Than You Think
#3[dead]
Re: RAG Is Simpler Than You Think
#4Maybe 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 queries. Does every LLM task need a full blown search engine? Why not a tightly scoped domain API for data retrieval?
Re: RAG Is Simpler Than You Think
#5Maybe 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…
It's just information retrieval packaged as something new.
Re: RAG Is Simpler Than You Think
#6I have a particular antipathy for articles too lazy to spell out acronyms on first use.
So: https://en.wikipedia.org/wiki/Retrieval-augmented_generation
Re: RAG Is Simpler Than You Think
#7The article sounds like AI slop with some predictable tells like short punctual sentences, bizarre jargon, and titles like "Recipe 4: On-The-Fly Embedding (The Fresh Data Play)"
Can we not reward junk like this? Most of the sentences are incomprehensible and provide zero actual argumentation, it's just a list of "whats" with no "whys"
Re: RAG Is Simpler Than You Think
#8There have been many blogs like this over the last years. Yes, embeddings are computationally heavy, but they are not at all complicated and they provide a lot of benefit. 90% of "document" based RAG projects should view semantic search with embeddings as their primary method. It's very powerful and so easy to implement that you could try it out and discover whether performance would be an issue rather than trying to…
Embeddings are reasonably simple, but it’s a journey to get there, and I am very proud of the dog-heavy explainer I wrote on them: https://sgnt.ai/p/embeddings-explainer/
Re: RAG Is Simpler Than You Think
#9Maybe 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…
It's just information retrieval packaged as something new.
And you can't fundraise on some old "information retrieval".
Re: RAG Is Simpler Than You Think
#10> Why this is more flexible than embeddings
Oh boy...