alt Hacker NewsGrep 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.
Replies
dv_dt • today at 6:40 PM
If the data is this large then why not ask the llm to build a query
➕ show 3 replies
dmyriel • today at 7:05 PM
[flagged]
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.