Contextual Retrieval • Hacker News Board

Re: Contextual Retrieval

#71

Post by cubefox » Sat, Sep 21, 2024, 12:39 PM UTC

jiggawatts wrote: post #62

_kb wrote: post #61

Earlier quoted context omitted.

A lot of people here (myself included) work across different specialisations and are here to learn from discussion that is intentionally unfamiliar.

Yes, but ChatGPT knows these things! Just ask it to expand the acronyms. This is the new “can you Google that for me?”

Another solution is to downvote / not upvote comments which place an unreasonable burden on the reader. The best comments are those which can be broadly understood without a need for Googling acronyms or "expanding" the comment using an LLM.

Re: Contextual Retrieval

#72

Post by captaindiego » Sat, Sep 21, 2024, 5:44 PM UTC

santiagobasulto wrote: post #68

williamcotton wrote: post #36

Earlier quoted context omitted.

Could you explain or link to explanations of all of the acronyms you’ve used in your comment?

These are all "techniques" on top of the foundations of RAG. It's similar to "Chain of Thought" in prompt engineering. You have an underlying technology, and then come up with techniques/frameworks on top. What MVC was for Web dev +15 years ago. RAPTOR for example is a technique that groups and clusters documents together, summarizes them, and creates embeddings defining a sort of a Tree. Paper: https://arxiv.org/htm…

Worth noting that a lot of the improvement gains you get from RAPTOR are (from my use cases) related to giving context to the chunks. Simpler but easier to implement methods of summarizing context (e.g. in a hierarchical document) and cutting chunks around document boundaries can get you most of the way there with less effort (again, as other mentioned, it depends though on your use)

Re: Contextual Retrieval

#73

Post by danielcampos93 » Mon, Sep 23, 2024, 3:08 PM UTC

postalcoder wrote: post #17

jillesvangurp wrote: post #5

Earlier quoted context omitted.

You could do a lot of stuff with pre-calculating things for your embeddings. Why cache when you can pre-calculate. That brings into play a whole lot of things people commonly do as part of ETL. I come from a traditional search back ground. It's quite obvious to me that RAG is a bit of a naive strategy if you limit it to just using vector search with some off the shelf embedding model. Vector search simply isn't that…

Graph RAG is very cool and outstanding at filling some niches. IIRC, Perplexity's actual search is just BM25 (based a lex fridman interview of the founder).

That is a funny was of explaining that they scrape google.