We replaced RAG with a virtual filesystem for our AI documentation assistant

Re:We replaced RAG with a virtual filesystem for our AI docu... by senordevnyc on Friday April 03, 2026 @11:44PM (#47635482)

Honestly, just from this question, I think you know enough that I’d go spend $20/month for a subscription to Codex, Claude Code, or Cursor, and ask them to teach you all this. I bet if you put in your comment verbatim with Opus 4.6 and went back and forth a bit, it could help you figure out exactly what you need and build a first version in a couple hours. Seriously, if you know the fundamentals and can poke and prod, these tools are amazing for helping expand your knowledge base. And constraints like how much you want to pay are excellent for steering the models. Seriously, just try it!

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by lelanthran on Saturday April 04, 2026 @03:49AM (#47636856)

> Honestly, just from this question, I think you know enough that I’d go spend $20/month for a subscription to Codex, Claude Code, or Cursor, and ask them to teach you all this.

Paying $20/m sounds like overkill. I have tabs open for all of the most well-known AI chatbots. Despite trying my hardest, it is not possible to exhaust your free options just by learning.

Hell, just on the chatbots alone, small projects can be vibe-coded too! No $20/m necessary.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by senordevnyc on Saturday April 04, 2026 @11:29AM (#47639876)

Yeah, but when it comes to actually building stuff, using Codex is night and day different from using ChatGPT.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by lelanthran on Saturday April 04, 2026 @01:16PM (#47641092)

> Yeah, but when it comes to actually building stuff, using Codex is night and day different from using ChatGPT.

Sure, but that wasn't what you recommended Codex for, was it?

>>> Honestly, just from this question, I think you know enough that I’d go spend $20/month for a subscription to Codex, Claude Code, or Cursor, and ask them to teach you all this.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by justinclift on Saturday April 04, 2026 @02:12PM (#47641670)

You don't need to pay an external crowd for that.

You can run Claude Code using a local instance of ~recent Ollama fine, and it'll do the teaching job perfectly well using (say) Qwen 3.5.

Doesn't even need to be one of the large models, one of the mid-size ones that fit in ~16GB of ram when given 128k+ context size should be fine.

[ Parent | on HN ]