Why not a simple full text search in Postgres ?
We replaced RAG with a virtual filesystem for our AI documentation assistant
61–70 of 190 posts
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#62The real thing I think people are rediscovering with file system based search is that there’s a type of semantic search that’s not embedding based retrieval. One that looks more like how a librarian organizes files into shelves based on the domain. We’re rediscovering forms of in search we’ve known about for decades. And it turns out they’re more interpretable to agents. https://softwaredoug.com/blog/2026/01/08/seman…
Someone simply assumed at some point that RAG must be based on vector search, and everyone followed.
I don't think this was a simple assumption. LLMs used to be much dumber!
GPT-3 era LLMS were not good at grep, they were not that good at recovering from errors, and they were not good at making followup queries over multiple turns of search. Multiple breakthroughs in code generation, tool use, and reasoning had to happen on the model side to make vector-based RAG look like unnecessary complexity
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#63I love the multipronged attack on RAG
RIP RAG: lasted one year at a skillset that recruiters would list on job descriptions, collectively shut down by industry professionals
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#64[dead]
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#65So you did GraphRAG but your graph is a filesystem tree.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#66Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#67[flagged]
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#68But SQLite is notoriously 35% faster than the filesystem [0], so why not use that? [0] https://news.ycombinator.com/item?id=14550060
And Turso has built a Virtual Filesystem on top of their SQLite.
AgentFS https://agentfs.ai/ https://github.com/tursodatabase/agentfs
Which sounds like a great idea, except that is uses NFS instead of FUSE (note that macFUSE now has a FSKit backend so FUSE seems like the best solution for both Mac and Linux).
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#69And you did not teach it to access chroma directly, because there is no adapter? Or because it is so much better at using FS tooling?
But in the end, I would expect, that you could add a skill / instructions on how to use chromadb directly
To be honest, I have no idea what chromadb is or how it works. But building an overlay FS seems like quite lot of work.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#70[dead]