This is very interesting, are there any examples of interacting with LLMs? If the queries are compiled and loaded into the database ahead of time the pattern of asking an LLM to generate a query from a natural language request seems difficult because current LLMs aren't going to know your query language yet and compiling each query for each prompt would add unnecessary overhead.
rohanrao123 23 minutes ago [-]
Congrats on the launch! I'm one of the authors of that paper you cited, glad it was useful and inspiring to building this :) Let me know if we can support in any way!
hbcondo714 3 hours ago [-]
Congrats! Any chance Helixdb can be run in the browser too, maybe via WASM? I'm looking for a vector db that can be pre-populated on the server and then be searched on the client so user queries (chat) stay on-device for privacy / compliance reasons.
GeorgeCurtis 3 hours ago [-]
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
raufakdemir 10 minutes ago [-]
How can I migrate neo4j to this?
GeorgeCurtis 7 minutes ago [-]
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
huevosabio 3 hours ago [-]
Can I run this as an embedded DB like sqlite?
Can I sidestep the DSL? I want my LLMs to generate queries and using a new language is going to make that hard or expensive.
GeorgeCurtis 2 hours ago [-]
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.
Attummm 56 minutes ago [-]
It sounds very intriguing indeed. However, the README makes some claims. Are there any benchmarks to support them?
> Built for performance we're currently 1000x faster than Neo4j, 100x faster than TigerGraph
GeorgeCurtis 52 minutes ago [-]
Those were actual benchmarks that we run, we didn't get a chance to write them out before posting. I'll get on it now and notify by replying to this comment when they're on the readme :)
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.
J_Shelby_J 3 hours ago [-]
How do you think about building the graph relationships? Any special approaches you use?
GeorgeCurtis 3 hours ago [-]
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?
SchwKatze 4 hours ago [-]
Super cool!!! I'll try it this week and go back to give a feedback.
GeorgeCurtis 3 hours ago [-]
I look forward to it :)
elpalek 2 hours ago [-]
What method/model are you using for sparse search?
GeorgeCurtis 2 hours ago [-]
We're going to use BM25. Currently it is just dense search. Coming very soon
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?
carlhjerpe 3 hours ago [-]
Nice "I'll have this name" when there's already the helix editor :)
GeorgeCurtis 3 hours ago [-]
First I'm hearing from it. The Beatles must've been super pissed when Apple took their name :(
That being said, when I saw `helix-db` I was thrown too. "What's a text editor doing writing a vector-graph database, I thought they were working on plugins?"
GeorgeCurtis 2 hours ago [-]
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.
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 :)
carlhjerpe 2 hours ago [-]
It's not the end of the world, just me being a bit grumpy. I mean it when I say good luck! :)
GeorgeCurtis 1 hours ago [-]
Thank you :)
bbatsell 2 hours ago [-]
I can't tell if this is droll sarcasm, but just in case not...
perhaps it’s a homage to the famous Helix database (see Wikipedia)
GeorgeCurtis 2 hours ago [-]
well noted
javierluraschi 3 hours ago [-]
What is the max number of dimensions supported for a vector?
GeorgeCurtis 3 hours ago [-]
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.
mdaniel 2 hours ago [-]
> so much easier that it’s worth a bit of a learning curve
I think you misspelled "vendor lock in"
GeorgeCurtis 1 hours ago [-]
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
sync 4 hours ago [-]
Looks nice! Are you looking to compete with https://www.falkordb.com or do something a bit different?
GeorgeCurtis 4 hours ago [-]
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
basonjourne 2 hours ago [-]
why not surrealdb?
GeorgeCurtis 9 minutes ago [-]
General consensus is it's really slow, I like the concept of surreal though. The 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)
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
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
Can I sidestep the DSL? I want my LLMs to generate queries and using a new language is going to make that hard or expensive.
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.
> Built for performance we're currently 1000x faster than Neo4j, 100x faster than TigerGraph
I.e: You have to re-index all of the vectors when you make an update to them.
Does that answer your question properly?
I'm surprised none in the team searched crates.io once before picking the name. Good luck!
https://github.com/helix-editor/helix/discussions/7038
That being said, when I saw `helix-db` I was thrown too. "What's a text editor doing writing a vector-graph database, I thought they were working on plugins?"
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.
https://en.wikipedia.org/wiki/Helix_(database)
https://en.wikipedia.org/wiki/Apple_Corps_v_Apple_Computer
I think you misspelled "vendor lock in"
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