thanks for the question! we chose f64 as a default for now as just to cover all cases and we believed that basic vector operations would not be our bottleneck initially. As we optimize our HNSW implementation, we are going to add support for f32 and binary vectors and drop using Vec<f64/f32> and instead use [f64/f32; {num_dimensions}] to avoid unnecessary heap allocation!

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? :)

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 :)

Neo4j supports vector indexes

to add to George's reply, for helix to run on the browser with WASM the storage engine has to be completely in memory. At the moment we use LMDB which uses file based storage so that does't work with the browser. As George said, we plan on making our own storage engine and as part of that we aim to have an in-memory implementation.

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

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.

Thanks for the kind words! At the moment the query language transpilation is quite unstable but we are in the process of a large remodel which we aim to finish in the next day or so. This will make the query language compilation far more robust, and will return helpful error messages (like the rust compiler). The other thing is the core traversals are currently single threaded, so aggregating huge lists of graph items can take a bit of a hit. Note however, that we are also implementing parallel LMDB iterators with the help of the meilisearch guys to make aggregation of large results much faster.

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.

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.

Assuming you are using GPUs for model inference, the best way to set it up would have the DB and a separate server to send inference requests. Note that we plan on support custom model endpoints and on the database side so you probably won't need the inference server in the future!

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?

I have been happily using Gel (formerly EdgeDB) for a few projects. I'm curious what you think it is missing in regards to hitting the "graph spot"?

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.

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.

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 :)

First I'm hearing from it. The Beatles must've been super pissed when Apple took their name :(

perhaps it’s a homage to the famous Helix database (see Wikipedia)

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?

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

I look forward to it :)

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.

We're going to use BM25. Currently it is just dense search. Coming very soon

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

apart from the fact Cozo seems to be pretty dead, we use a different storage engine which makes our reads much faster. based on their benchmarks I estimate our most of our reads to be 10x faster. I think our query language is much simpler, and easy to understand than Datalog which is what they use.

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

On comparable benchmarks with comparable guarantees? Comparable persistence levels? I’m very skeptical.

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.

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

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

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)