←back to thread

Production RAG: what I learned from processing 5M+ documents

(blog.abdellatif.io)
548 points tifa2up | 2 comments | 20 Oct 25 15:55 UTC | HN request time: 0s | source
Show context
alexchantavy ◴[20 Oct 25 16:47 UTC] No.45646021[source]▶
> What moved the needle: Query Generation

What does query generation mean in this context, it’s probably not SQL queries right?

replies(2): >>45646127 #>>45646638 #
daemonologist ◴[20 Oct 25 16:52 UTC] No.45646127[source]▶
It's described in the remainder of the point - they use an LLM to generate additional search queries, either rephrasings of the user's query or bringing additional context from the chat history.
replies(1): >>45646598 #
1. goleary ◴[20 Oct 25 17:28 UTC] No.45646598[source]▶
Here's an interesting read on the evolution beyond RAG: https://www.nicolasbustamante.com/p/the-rag-obituary-killed-...

One of the key features in Claude Code is "Agentic Search" aka using (rip)grep/ls to search a codebase without any of the overhead of RAG.

Sounds like even RAG approaches use a similar approach (Query Generation).

replies(1): >>45647758 #
2. smokel ◴[20 Oct 25 18:58 UTC] No.45647758[source]▶
The article raises several interesting points, but I find its claim that Claude Code relies primarily on grep for code search unconvincing. It's clear that Claude Code can parse and reason about code structure, employing techniques far beyond simple regex matching. Since this assumption underpins much of the article's argument, it makes me question the overall reliability of its conclusions a bit.

Or am I completely misunderstanding how Claude Code works?