[dead]
We replaced RAG with a virtual filesystem for our AI documentation assistant
81–90 of 190 posts
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#82This is one of the most confusing claims I've seen in a long time. Grep and others over files would be the equivalent of an old fashioned keyword search where most RAG uses vector search. But everything else they claim about a file system just suggests that they don't know anything about databases. I'm not familiar with how most out of the box RAG systems categorize data, but with a database you can index content lit…
Yeah I’ve had a lot of success with agentic search against a database.
The way I think of it, the main characteristic of agentic search is just that the agent can execute many types of adhoc queries
It’s not about a file system
As I understood it early RAG systems were all about performing that search for the agent - that’s what makes that approach “non agentic”
But when I have a database that has both embeddings and full text and you can query against both of those things and I let the agent execute whatever types of queries it wants - that’s “agentic search” in my book
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#83This is one of the most confusing claims I've seen in a long time. Grep and others over files would be the equivalent of an old fashioned keyword search where most RAG uses vector search. But everything else they claim about a file system just suggests that they don't know anything about databases. I'm not familiar with how most out of the box RAG systems categorize data, but with a database you can index content lit…
I didn't get into the details too much, but I kept thinking, why isn't he just having an agent discover things from various data sources? I've had much better success with that.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#84The 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…
My intuition is that since AI assistants are fictional characters in a story being autocompleted by an LLM, mechanisms that are interpretable as human interactions with language and appear in the pretraining data have a surprising advantage over mechanisms that are more like speculation about how the brain works or abstract concepts.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#85The 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.
Certainly a lot of blog posts followed. Not sure that “everyone” was so blinkered.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#86The 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…
My intuition is that since AI assistants are fictional characters in a story being autocompleted by an LLM, mechanisms that are interpretable as human interactions with language and appear in the pretraining data have a surprising advantage over mechanisms that are more like speculation about how the brain works or abstract concepts.
This is also why LLMs get 80% of the way there and crap out on logic. They were trained on all the open source abandonware on GitHub.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#87The title says you replaced RAG, but ChromaFs is still querying Chroma on every command — you replaced RAG's interface, not RAG itself. Which is actually the more interesting finding: the retrieval was never the bottleneck, the abstraction was.
Agents don't need better search. They need `grep`.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#88This is one of the most confusing claims I've seen in a long time. Grep and others over files would be the equivalent of an old fashioned keyword search where most RAG uses vector search. But everything else they claim about a file system just suggests that they don't know anything about databases. I'm not familiar with how most out of the box RAG systems categorize data, but with a database you can index content lit…
Yeah I’ve had a lot of success with agentic search against a database. The way I think of it, the main characteristic of agentic search is just that the agent can execute many types of adhoc queries It’s not about a file system As I understood it early RAG systems were all about performing that search for the agent - that’s what makes that approach “non agentic” But when I have a database that has both embeddings and…
Absolutely, agentic search is much more robust to the specific implementation details of your search setup (data quality issues, too) than the early one-shot approaches were. Anyone watching Claude Code work can see this for themselves.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#89Earlier 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…
Yeah, some of the uplift people are anecdotally seeing from “just using the filesystem” is, imo, on account of how difficult it is to take a principled approach to pre-chunking when implementing other approaches.
Re: We replaced RAG with a virtual filesystem for our AI documentation assistant
#90The 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…
And next, we’ll get to tag based file systems