Grep is the fastest tool for many things, but for production RAG it cannot search with meaning, different languages or typos like hybrid vector search can. And it won't scale on terabytes of documents across distributed servers if you want to say under 1000ms.

▲

ozkatz 2 days ago | parent | next [-]

all true for a single grep invocation, however a capable LLM can drive grep using similar terms (`grep (red|maroon|scarlet|crimson)`, moving the measure of similarity from embedding/indexing time to inference time. There's benefits to that.

▲

jdthedisciple 2 days ago | parent [-]

> red|maroon|scarlet|crimson

still doesn't include typo'ed variants for any of these

▲

ozkatz 2 days ago | parent [-]

but a good combination of prompt, harness and model will easily close that gap. a more advanced (but equivalent) form of grep could also offer fuzzy matching/levenshtein distance function to augment that.

	▲	everforward 2 days ago \| parent \| next [-]
		It will, but it does so by burning tokens. I'm sure you've also seen the output of an overly eager grep by an LLM. I think we're verging on the point where people will care more about the most token-efficient ways to do a task than the lowest human effort version. Humans are expensive, humans using half as many tokens are cheaper.
	▲	c-hendricks 2 days ago \| parent \| prev [-]
		This sounds like AOT vs JIT weights.

▲

dv_dt 2 days ago | parent | prev | next [-]

If the data is this large then why not ask the llm to build a query

	▲	itishappy 2 days ago \| parent \| next [-]
		That's more-or-less what RAG is; a tool to surface relevant data so that AI can make informed decisions. Efficient retrieval is important so that AI doesn't need to ingest the whole corpus for each query.
	▲	aaroninsf 2 days ago \| parent \| prev \| next [-]
		My case: With a very large dataset of totally unnormalized data, semantic folding is a silver bullet.
	▲	nostrebored 2 days ago \| parent \| prev [-]
		latency is often the reason, distilling interactions into significantly better retrieval is the second.

▲

dmyriel 2 days ago | parent | prev [-]

[flagged]