Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

mintlify.com

Post reply on HN
Print view View original

111–120 of 190 posts

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

#111

Post by girvo »

tensor wrote: post #80
brap wrote: post #77

Earlier quoted context omitted.

I get what you’re saying, and you’re right, however I can also see where they’re coming from: Empirically, agents (especially the coding CLIs) seem to be doing so much better with files, even if the tooling around them is less than ideal. With other custom tools they instantly lose 50 IQ points, if they even bother using the tools in the first place.

Sorry, this still makes no sense. LLMs don't care about files. The way most codings systems work is that they simply provide the whole file to the LLM rather than a subset of it. That's just a choice in how you implemented your RAG search system and database. In this case the "record" is big, a file. No doubt that works for code, but it's nonsensical outside that. E.g. for wikipedia the logical unit would likely be a…

They've been RLHF'd to the nth degree around working with *nix tools and filesystems, in practice.

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

#112

Post by girvo »

stuaxo wrote: post #106
slp3r wrote: post #79

This feels like massive overengineering just to bypass naive chunking. Emulating a POSIX shell in TS on top of ChromaDB to do hierarchical search is going to destroy your TTFT. Every ls and grep the agent decides to run is a separate inference cycle. You're just trading RAG context-loss for severe multi-step latency

Could totally have FUSE over the chunks and then there is no shell emilation.

I'll be honest that's what I expected to read about!

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

#113

Post by rao-v »

softwaredoug wrote: post #2

The 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…

I got to say people also seem to be missing really simple tricks with RAG that help. Using longer chunks and appending the file path to the chunk makes a big difference.

Having said that, generally agree that keyword searching via rg and using the folder structure is easier and better.

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

#114

Post by 3abiton »

rao-v wrote: post #113
softwaredoug wrote: post #2

The 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…

I got to say people also seem to be missing really simple tricks with RAG that help. Using longer chunks and appending the file path to the chunk makes a big difference. Having said that, generally agree that keyword searching via rg and using the folder structure is easier and better.

> I got to say people also seem to be missing really simple tricks with RAG that help. Using longer chunks and appending the file path to the chunk makes a big difference. > > Having said that, generally agree that keyword searching via rg and using the folder structure is easier and better.

It depends on the task no? Codebase RAG for example has arguably a different setup than text search. I wonder how much the FS "native" embedding would help.

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

#116

Post by huflungdung »

neuzhou wrote: post #98
softwaredoug wrote: post #2

The 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…

[flagged]

[dead]

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

#117

Post by bitwize »

What if... each agent had its own virtual file system, and anything the agent needed to access was accessible as files in the filesystem?

Congratulations, you just reinvented Plan 9. I think we're going to end up reinventing a lot of things in computing that we discovered and then forgot about because Apple/Microsoft/Google couldn't monetize them, "because AI". And I don't know how to feel about that.

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

#118

Post by baby »

softwaredoug wrote: post #2

The 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…

Yep, I was using RAG for all sorts of stuff and now moved everything to just rg+fd+cd+ls, much faster, easier, etc.

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

#119

Post by danelliot »

rao-v wrote: post #113
softwaredoug wrote: post #2

The 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…

I got to say people also seem to be missing really simple tricks with RAG that help. Using longer chunks and appending the file path to the chunk makes a big difference. Having said that, generally agree that keyword searching via rg and using the folder structure is easier and better.

[dead]

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

#120

Post by siva7 »

neuzhou wrote: post #98
softwaredoug wrote: post #2

The 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…

[flagged]

> Switched to just letting the agent browse the directory tree and read files on demand -- it figured out the module structure in about 30 seconds

You guess what's the difference between code and loosely structured text...

Post reply on HN