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

From zero to a RAG system: successes and failures

en.andros.dev

Post reply on HN
Print view View original

11–20 of 129 posts

Re: From zero to a RAG system: successes and failures

#11

Post by mentos »

JKCalhoun wrote: post #10

And some have been saying that RAGs are obsolete—that the context window of a modern LLM is adequate (preferable?). The example I recently read was that the contexts are large enough for the entire "The Lord of the Rings" books. That may be, but then there's an entire law library, the entirety of Wikipedia (and the example in this article of 451 GB). Surely those are at least an order of magnitude larger than Tolkien…

I assume it’s not possible to get the same results by fine tuning a model with the documents instead?

Re: From zero to a RAG system: successes and failures

#12

Post by notglossy »

mentos wrote: post #11
JKCalhoun wrote: post #10

And some have been saying that RAGs are obsolete—that the context window of a modern LLM is adequate (preferable?). The example I recently read was that the contexts are large enough for the entire "The Lord of the Rings" books. That may be, but then there's an entire law library, the entirety of Wikipedia (and the example in this article of 451 GB). Surely those are at least an order of magnitude larger than Tolkien…

I assume it’s not possible to get the same results by fine tuning a model with the documents instead?

You will still get hallucinations. With RAG you use the vectors to aid in finding things that are relevant, and then you typically also have the raw text data stored as well. This allows you to theoretically have LLM outputs grounded in the truth of the documents. Depending on implementation, you can also make the LLM cite the sources (filename, chunk, etc).

Re: From zero to a RAG system: successes and failures

#14

Post by Nihilartikel »

JKCalhoun wrote: post #10

And some have been saying that RAGs are obsolete—that the context window of a modern LLM is adequate (preferable?). The example I recently read was that the contexts are large enough for the entire "The Lord of the Rings" books. That may be, but then there's an entire law library, the entirety of Wikipedia (and the example in this article of 451 GB). Surely those are at least an order of magnitude larger than Tolkien…

I'm not super deep on LLM development, but with ram being a material bottleneck and from what I've read about DeepSeek's results with offloading factual knowledge with 'engrams' I think that the near future will start moving towards the dense core of LLMs focusing much more on a distillation of universal reasoning and logic while factual knowledge is pushed out into slower storage. IIRC Nvidia's Nemotron Cascade is taking MoE even further in that direction too.

I don't need a coding model to be able to give me an analysis of the declaration of independence in urdu from 'memory' and the price in ram for being able to do that, impressive as it is, is an inefficiency.

Re: From zero to a RAG system: successes and failures

#15

Post by menaerus »

JKCalhoun wrote: post #10

And some have been saying that RAGs are obsolete—that the context window of a modern LLM is adequate (preferable?). The example I recently read was that the contexts are large enough for the entire "The Lord of the Rings" books. That may be, but then there's an entire law library, the entirety of Wikipedia (and the example in this article of 451 GB). Surely those are at least an order of magnitude larger than Tolkien…

The success of the model responding to you with a correct information is a function of giving it proper context too.

That hasn't changed nor I think it will, even with the models having very large context windows (eg Gemini has 2M). It is observed that having a large context alone is not enough and that it is better to give the model sufficiently enough and quality information rather than filling it with virtually everything. Latter is also impossible and does not scale well with long and complicated tasks where reaching the context limit is inevitable. In that case you need to have the RAG which will be smart enough to extract the sufficient information from previous answers/context, and make it part of the new context, which in turn will make it possible for the model to keep its performance at satisfactory level.

Re: From zero to a RAG system: successes and failures

#18

Post by alansaber »

JKCalhoun wrote: post #10

And some have been saying that RAGs are obsolete—that the context window of a modern LLM is adequate (preferable?). The example I recently read was that the contexts are large enough for the entire "The Lord of the Rings" books. That may be, but then there's an entire law library, the entirety of Wikipedia (and the example in this article of 451 GB). Surely those are at least an order of magnitude larger than Tolkien…

RAG is nowhere near obselete. Model performance on enormous sequences degrades hugely as they are not well represented in training and non quadratic attention approximations are not amazing

Re: From zero to a RAG system: successes and failures

#20

Post by civeng »

Great write-up. Thank you! I’m contemplating a similar RAG architecture for my engineering firm, but we’re dealing with roughly 20x the data volume (estimating around 9TB of project files, specs, and PDFs). I've been reading about Google's new STATIC framework (sparse matrix constrained decoding) and am really curious about the shift toward generative retrieval for massive speedups well beyond this approach. For those who have scaled RAG into the multi-terabyte range: is it actually worth exploring generative retrieval approaches like STATIC to bypass standard dense vector search, or is a traditional sharded vector DB (Milvus, Pinecone, etc.) still the most practical path at this scale?

I would guess the ingestion pain is still the same.

This new world is astounding.

Post reply on HN