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

Re:Production RAG: what I learned from processing 5M+ documents by alexchantavy on Monday October 20, 2025 @12:47PM (#45646021)

> What moved the needle: Query Generation

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

[ Parent | on HN ]

Re:Production RAG: what I learned from processing 5M+ documents by andreasgl on Monday October 20, 2025 @01:32PM (#45646638)

I think they mean query expansion: https://en.wikipedia.org/wiki/Query_expansion

[ Parent | on HN ]

Re:Production RAG: what I learned from processing 5M+ documents by daemonologist on Monday October 20, 2025 @12:52PM (#45646127)

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.

[ Parent | on HN ]

Re:Production RAG: what I learned from processing 5M+ documents by goleary on Monday October 20, 2025 @01:28PM (#45646598)

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).

[ Parent | on HN ]

Re:Production RAG: what I learned from processing 5M+ documents by smokel on Monday October 20, 2025 @02:58PM (#45647758)

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?

[ Parent | on HN ]