HNHacker News
TopNewBestAskShowJobs

GeorgeCurtis

173 karma · joined March 17, 2023

Working on helix-db.com

https://x.com/georgecurtiss

submissionscomments
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
We started as a graph database, so that's definitely the main thing we want to get right and we wan't to prioritise capturing all that functionality.

We have a python SDK already! What do you mean by generated types though?

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Looking forward to putting you at ease :) Working on some proper benchmarks over the next few days.
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
We are open-source, so you can use and self host us for free. Our plan is to create a managed service (so long as all goes well) which shouldn't be priced any differently from other databases in the space.

We chose AGPL to make sure someone can't make a cloud hosted version of our product, think MongoDB on AWS a few years back.

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
No, we are in the process of writing up some proper benchmarks. Our first user used us to build MuskMap and TrumpMap, which went viral on twitter. Not sure how it compared to other graph DBs at the time (bear in mind this was v1 and very bear bones), but it got latency of using Postgres >5s down to 50ms with us.
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
We don't have any benchmarks against them but from what I've just read about there bench marks, we should be just as good as them.

That is just heresy though, am interested myself now and will run some proper benchmarks

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
So far, we've tested it for up to ~10B connections and 50 odd million nodes. We didn't run in to any problems with it yet.
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
gel is a relational database, have you been building with it under a graph type philosophy?
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Neo4j first of all is very slow for vectors, so if performance is something that matters for your user experience they definitely aren't a viable option. This is probably why Neo4j themselves have released guides on how to build that middleman software I mentioned with Qdrant for viable performance.

Furthermore, the vectors is capped at 4k dimensions which although may be enough most of the time, is a problem for some of the users we've spoken to. Also, they don't allow pre filtering which is a problem for a few people we've spoken to including Zep AI. They are on the right track, but there are a lot of holes that we are hoping to fill :)

Edit: AND, it is super memory intensive. People have had problems using extremely small datasets and have had memory overflows.

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
The fortunate thing about our vector DB, like I mentioned in the post, is that we store the HNSW on disk. So, it is much less intense on your memory. Similar thing to what turbo puffer has done.

With regard to the graph db, we mostly use our laptops to test it and haven't run into an issue with performance yet on any size dataset.

If you wanna chat DM me on X :)

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Partly because they're working with a monolith that I imagine is difficult to iterate on and it's written in Java. We've had the benefit of working on this in Rust which lets us get really nitty and gritty with different optimisations.

My friend who I worked on this with is putting together a technical blog on those graph optimisations so I'll link it here when he's done

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
This is definitely a problem we want to work on fixing quickly. We're currently planning an MCP tool that can traverse the graph and decide for itself at each step where to go to next. As opposed to having to generate actual text written queries.

I mentioned in another comment that you can provide a grammar with constrained decoding to force the LLM to generate tokens that comply with the grammar. This ensures that only valid syntactic constructs are produced.

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Wow! I enjoyed reading it a lot and it was definitely inspiring for this project!

Would love to talk to you about it and make sure we capture all of the pain points if you're open to it? :)

GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
We can build an ingestion engine for you :)

We've built SQL and PGVector ones already, just waiting for someone who could make use of other ones before we build them.

Let us know! Twitter in my bio

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
General consensus is it's really slow, I like the concept of surreal though. Our first, and extremely bare bones, version of the graph db was 1-2 orders of magnitude faster than surreal (we haven't run benchmarks against surreal recently, but I'll put them here when we're done)
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Those were actual benchmarks that we run, we didn't get a chance to write them out properly before posting. I'll get on it now and notify by replying to this comment when they're on the readme :)
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
You can literally use us for free haha. There's not a language that properly encapsulates graph and vector functionality, so we needed to make our own. Also, we thought it was dumb that query languages weren't type-safe... So we changed that
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
There was no active one. We saw this and thought it would be a nice nod to history. We've actually spoken to some developers at apple who thought this was really neat :)
GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
Thank you :)
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Looks really interesting, I'll have a proper read. What would be your reasoning to incorporate this if we already have vector functionality and semantic search?
GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
We're going to use BM25. Currently it is just dense search. Coming very soon
GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
Currently you can't run us embedded and I'm not sure how you could sidestep the DSL :/

We're working on putting our grammar in llama's cpp code so that it only outputs grammatically correct HQL. But, even without that it shouldn't be hard or expensive to do. I wrote a Claude wrapper that had our docs in its context window, it did a good job of writing queries most of the time.

GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
well noted
GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
we just started off as a side project and thought the name fitted well. With the strands, graph type structure, connections...

We didn't think of getting people to use it until we found it was solving a real pain point for people, so weren't worried about trademarks or names. There was no other helix db so that was good enough for us at the time.

GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
There is currently no cap. We will probably impose a similar cap to Qdrant or Pinecone some time soon ~64k. There's obviously a performance trade off as you go up, but we hope to massively offset this by doing binary quantisation within the next couple of months.
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
First I'm hearing from it. The Beatles must've been super pissed when Apple took their name :(
GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
Pretty much the same way you would with any graph DB, with the added benefit of being able to treat a vector as a node by creating those explicit relationships between them.

Does that answer your question properly?

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Interesting, we've had a few people ask about this. So essentially you'd call the server to retrieve the HNSW and then store it in the browser and use WASM to query it?

Currently the road block for that is the LMDB storage engine. We have on our own storage engine on our roadmap, which we want to include WASM support with. If you wanna talk about it reach out to my twitter: https://x.com/georgecurtiss

GeorgeCurtis··on Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)
I look forward to it :)
GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Kuzu don't support incremental indexing on the vectors. The vector index is completely separate and decoupled from the graph.

I.e: You have to re-index all of the vectors when you make an update to them.

GeorgeCurtis··on Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)
Pretty much, our biggest focus is on Graph and Hybrid RAG. They seem to have really honed in on Graph RAG since the last time I checked their website.

One of the problems I know people experience with them is that they're super slow at bulk reading.

Oh also, they aren't built in Rust haha

← PreviousPage 2 of 3Next →