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 pboulos on Friday April 03, 2026 @02:04PM (#47629921)

I think this is a great approach for a startup like Mintlify. I do have skepticism around how practical this would be in some of the “messier” organisations where RAG stands to add the most value. From personal experience, getting RAG to work well in places where the structure of the organisation and the information contained therein is far from hierarchical or partition-able is a very hard task.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by khalic on Friday April 03, 2026 @02:19PM (#47630100)

The use case is well defined here, let’s not jump the gun. Text search, like with code, is a relatively simple problem compared to intrinsic semantic content in a book for example. I think the moral here is that RAG is not a silver bullet, the claude code team came to the same conclusion.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by pboulos on Friday April 03, 2026 @03:25PM (#47630999)

I agree with your assessment.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by dominotw on Friday April 03, 2026 @04:32PM (#47631883)

> he claude code team came to the same conclusion.

github copilot uses rag

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by GandalfHN on Friday April 03, 2026 @03:41PM (#47631214)

Layering a virtual FS over a spaghetti-doc org is an indexer in drag, and you still need access control or it's a complaince disaster.

[ Parent | on HN ]

Re:We replaced RAG with a virtual filesystem for our AI docu... by skeptrune on Friday April 03, 2026 @02:30PM (#47630238)

Modern OCR tooling is quite good. If the knowledge you are adding into your search database is able to be OCR'd then I think the approach we took here is able to be generalized.

[ Parent | on HN ]