Earlier quoted context omitted.
[flagged]
Don't blame me, blame the people who invented the concept and wrote the original RAG paper. https://arxiv.org/pdf/2005.11401
[flagged]
Pruning RAG context down to what the answer actually needs
51–54 of 54 posts
Re: Pruning RAG context down to what the answer actually needs
#52Earlier quoted context omitted.
Don't blame me, blame the people who invented the concept and wrote the original RAG paper. https://arxiv.org/pdf/2005.11401
[flagged]
Backing a question about definition up with the actual source of the definition isn’t “dumb gatekeeping”. You feel that there is a right way to do RAG and you’ve written a framework that does it that way. That’s great.
I’m not the one who’s saying that certain things are not RAG so I don’t really see how I’m gatekeeping. I was actually trying to be helpful.
Re: Pruning RAG context down to what the answer actually needs
#53Earlier quoted context omitted.
RAG is a fancy acronym that basically boils down to: let's give ai agents the super power of information retrieval (aka. search) and "augment" the generation with a list of results by adding that to the context. The narrow interpretation of this is usually some kind of vector search. Which some people naively treat as magic pixie dust that will make search quality amazing without any tuning whatsoever. This does not…
As a real dummy on the subject, maybe you could help me understand where vector search tends to fall over? I use it to retrieve tool functions by description and it has worked very well for me, but I expect I'm in the "very simple use cases" category that you mentioned.
That is indeed a simple case. Imagine using that on your Google drive where you might have lots of variations of the same documents with names such as my-doc-draft.doc, my-doc-outdated.doc and my-doc-final-v0.1.3.doc. Which is the best version? Unless you add logic to control this, even the best vector search will not be able to tell apart outdated/incomplete/inaccurate data from the best data. That's why enterprise document search never really got good. Google's own drive is a good example of a search that isn't great.
A good example from an ecommerce vendor that now trains its own models is photo search. They used an off the shelf model to implement that when testing with a photo of some clothes, instead of getting similar products they got random products that featured the same person modeling completely different clothes. The model they used was biased towards faces rather than clothes.
Re: Pruning RAG context down to what the answer actually needs
#54Earlier quoted context omitted.
So when an agent does "cat file.txt" that's RAG to you?
The answer would be yes. It's about using stored knowledge to increase the accuracy of the answer and evidence surfacing. It doesn't have to be a vector database. Kapa is one of the few companies doing RAG right.
Your definition is diluted to the point of being worthless.