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

Your File System Is Already A Graph Database

rumproarious.com

Post reply on HN
Print view View original

41–50 of 85 posts

Re: Your File System Is Already A Graph Database

#41

Post by weitendorf »

itake wrote: post #10

I'm wonder though: 1. Why does AI need that folder structure? Why not a flat list of files and let the AI agent explore with BM25 / grep, etc. 2. pre-compute compression vs compute at query time. Kaparthy (and you) are recommending pre-compressing and sorting based on hard coded human abstraction opinions that may match how the data might be queried into human-friendly buckets and language. Why not just let the AI ca…

> Why does AI need that folder structure? Why not a flat list of files and let the AI agent explore with BM25 / grep, etc.

Progressive disclosure, same reason you don't get assaulted with all the information a website has to offer at once, or given a sql console and told to figure it out, and instead see a portion of the information in a way that is supposed to naturally lead you to finding the next and next bits of information you're looking for.

> use cases

This is essentially just where you're moving the hierarchy/compression, but at least for me these are not very disjoint and separable. I think what I actually want are adaptable LoRa that loosely correspond to these use cases but where a dense discriminator or other system is able to adapt and stay in sync with these too. Also, tool-calling + sql/vector embeddings so that you can actually get good filesystem search without it feeling like work, and let the model filter out the junk.

> let the AI calculate this at run time?

You still do want to let it do agentic RAG but I think more tools are better. We're using sqlite-vec, generating multimodal and single-mode embeddings, and trying to make everything typed into a walkable graph of entity types, because that makes it much easier to efficiently walk/retrieve the "semantic space" in a way that generalizes. A small local model needs at least enough structure to know these are the X ways available to look for something and they are organized in Y ways, oriented towards Z and A things.

Especially on-device, telling them to "just figure it out" is like dropping a toddler or autonomous vehicle into a dark room and telling them to build you a search engine lol. They need some help and also quite literally to be taught what a search engine means for these purposes. Also, if you just let them explore or write things without any kind of grounding in what you need/any kind of positive signals, they're just going to be making a mess on your computer.

Re: Your File System Is Already A Graph Database

#42

Post by embedding-shape »

weitendorf wrote: post #34
embedding-shape wrote: post #7

I've been playing around with the same, but trying to use local models as my Obsidian vault obviously contain a bunch of private things I'm not willing to share with for-profit companies, but I have yet to find any model that comes close to working out as well as just codex or cc with the small models, even with 96GB of VRAM to play around with. I've started to think about maybe a fine-tuned model is needed, specific…

This is exactly what we're working on, is there any application in particular you're interested in the most? > I'm struggling collecting actual data I could use for fine-tuning myself, Journalling or otherwise writing is by far the best way to do this IMO but it doesn't take very much audio to accurately do a voice-clone. The hard thing about journalling is that it can actually be really biased away from the actual "…

I think maybe you're misunderstanding the issue here. I have loads of data, but I'm unwilling to send it to 3rd parties, so that leaves me with gathering/generating the training data locally, but none of the models are good/strong enough for that today.

I'd love to "send them to go looking for stuff for you", but local models aren't great at this today, even with beefy hardware, and since that's about my only option, that leaves me unable to get sessions to use for the fine-tuning in the first place.

Re: Your File System Is Already A Graph Database

#43

Post by kenforthewin »

I keep harping on this, but the question is not "can you use your filesystem as a graph database" - of course you can - but whether this performs better or worse than a vector database approach, especially at scale.

The premise of Atomic, the knowledge base project I'm currently working on, is that there is still significant value in vectors, even in an agentic context. https://github.com/kenforthewin/atomic

Re: Your File System Is Already A Graph Database

#44

Post by zadikian »

On the other hand, I get why cloud drive users completely disregard file structure and search everything. Two files usually don't have the same name unless you're laying it out programmatically like this. I use dir trees for code ofc, but everything else is flat in my ~/Documents.

Deep inside a project dir, feels like some the ease of LLMs is just not having to cd into the correct directory, but you shouldn't need an LLM to do that. I'm gonna try setting up some aliases like "auto cd to wherever foo/main.py is" and see how that goes.

Re: Your File System Is Already A Graph Database

#46

Post by altmanaltman »

volemo wrote: post #29
stingraycharles wrote: post #22

Using the same logic, a key/value database is also a graph database? Isn’t the biggest benefit of graph databases the indexing and additional query constructs they support, like shortest path finding and whatnot?

I think the confusion stems from the fact that we call a database what is really a database management system.

You confuse the raw fist with the master who calculates the shortest path to your destruction.

Re: Your File System Is Already A Graph Database

#47

Post by zadikian »

lamasery wrote: post #28
sorokod wrote: post #23

Earlier quoted context omitted.

Yes, the author is likely unaware of this. They see markdown files with links, so a graph and the set of those files, so a "database". https://neo4j.com/docs/graph-data-science/current/algorithms...

Neo4j looooooves the "if you think about it, everything is graphs!" marketing maneuver. They (their marketing department) were the very first thing I thought of when I read this headline.

"Everything is graphs, so let's use a graph DBMS for anything" is a classic blunder

Re: Your File System Is Already A Graph Database

#48

Post by embedding-shape »

zadikian wrote: post #44

On the other hand, I get why cloud drive users completely disregard file structure and search everything. Two files usually don't have the same name unless you're laying it out programmatically like this. I use dir trees for code ofc, but everything else is flat in my ~/Documents. Deep inside a project dir, feels like some the ease of LLMs is just not having to cd into the correct directory, but you shouldn't need an…

> I use dir trees for code ofc, but everything else is flat in my ~/Documents.

Which is great, but on all major OSes you'd eventually hit performance issues with flat directories like this. Might not be an issue in month one, or even year one, but after 10 years of note taking/journaling that approach will show the issue with large flat directories.

So eventually you'd need to shard it somehow, so might as well start categorizing/sorting things from the get go, at least in some broad major categories at least, because doing so once you already have 10K entries in a directory, it sucks big time to do it.

Re: Your File System Is Already A Graph Database

#49

Post by Retr0id »

rleigh wrote: post #37
Retr0id wrote: post #33

Earlier quoted context omitted.

GP was talking about symlink cycles though, which can't produce orphans during deletion.

True, I missed that. I suppose with symlinks you have the reverse problem: you can point to deleted filenames and then have broken links. The cycle detection is still an issue though--it has indeterminate complexity and the graph can be modified as you are traversing it!

This is true, but just about everyone has a symlink cycle on their system at `/proc/self/root`, and for the most part nobody notices. Having a max recursion depth is usually more useful than actively trying to detect cycles.

Re: Your File System Is Already A Graph Database

#50

Post by weitendorf »

embedding-shape wrote: post #42
weitendorf wrote: post #34

Earlier quoted context omitted.

This is exactly what we're working on, is there any application in particular you're interested in the most? > I'm struggling collecting actual data I could use for fine-tuning myself, Journalling or otherwise writing is by far the best way to do this IMO but it doesn't take very much audio to accurately do a voice-clone. The hard thing about journalling is that it can actually be really biased away from the actual "…

I think maybe you're misunderstanding the issue here. I have loads of data, but I'm unwilling to send it to 3rd parties, so that leaves me with gathering/generating the training data locally, but none of the models are good/strong enough for that today. I'd love to "send them to go looking for stuff for you", but local models aren't great at this today, even with beefy hardware, and since that's about my only option,…

Right, that's exactly the situation I'm in too and "send them to go looking for stuff for you" without it going off the rails is the problem we've been working on.

Basically you need a squad of specialized models to do this in a mostly-structured way that ends up looking kind of like a crawling or scraping/search operation. I can share a stack of about 5-6 that are working for us directly if you want, I want to keep the exact stack on the DL for now but you can check my company's recent github activity to get an idea of it. It's basically a "browser agent" where gemma or qwen guide the general navigation/summarization but mostly focus on information extraction and normalization.

The other thing I've done, which obviously not everybody is going to want to do, is create emails and browser profiles for the browser agent (since they basically work when I'm not on the computer, but need identity to navigate the web) and run them on devices that don't have the keys to the kingdom. I also give them my phone number and their own (via an endpoint they can only call me from). That way if they run into something they have a way to escalate it, and I can do limited steering out of the loop. Obviously this is way more work than is reasonable for most people right now though so I'm hoping to show people a proper batteries-included setup for it soon.

Edit: Based on your other comment, I think maybe what you're really looking for most are "personal traces". Right now that's something we're working on with https://github.com/accretional/chromerpc (which uses the lower level Chrome Devtools Protocol rather than Puppetteer to basically fully automate web navigation, either through an LLM or prescriptive workflows). It would be very simple to set up automation to take a screenshot and save it locally every Xm or in response to certain events and generate traces for yourself that way, if you want. That alone provides a pretty strong base for a personal dataset.

Post reply on HN