I think their point is the size/performance tradeoff rather than outright performance. The point of TurboQuant is the size savings, while still giving high accuracy.
It's been a while, but I do recall some high-performing vector matching indexes being very large.
ghm2199 8 hours ago [-]
Wow! 4GB for 10 million documents. This means one could build a reverse index much faster than before and devx processes like debugging, performance testing would become much smoother. Can't wait for the sqlite bindings to come out!
ghm2199 8 hours ago [-]
Also the removal latency is on a log scale. Which is quite insane.
nharada 8 hours ago [-]
It would be nice to have the README be a little more human written for a project where you actually want people to adopt it
badatnames 7 hours ago [-]
Anthropic employee. This is what your brain on kool aid looks like
deeviant 7 hours ago [-]
Then again, if the only thing the human doing is bitching about AI use, it's not really that comparatively useful.
righthand 2 hours ago [-]
Sure it is useful, the bitching is canary in the shit software mine. How do you know the software isnt shit if the Readme is shit?
This looks perfect for local, privacy first search, but since it's built in Rust, has anyone tried compiling it to WASM to run directly inside a browser extension?
westurner 6 hours ago [-]
oxirs does embeddings and GraphRAG, and full text search with Tantivy; oxirs-vec, oxirs-graphrag
There's an oxirs-wasm with RDF and SPARQL bindings with a query budget. Tantivy-wasm says that the release WASM bundle is 1.5 MB.
No, WASM only has 128b SIMD instructions, for now.
cpursley 7 hours ago [-]
Also interested.
cat-whisperer 3 hours ago [-]
What's a good embedding model and search to run locally? something fast and lightweight.
beernet 6 hours ago [-]
Why not just use Qdrant? They've been integrating TurboQuant for months, works well.
kanungle 7 minutes ago [-]
Integrated in 5 weeks and just expanded data types for turbo4 in last release. No longer need to store fp32 vectors if you don't need them
OutOfHere 3 hours ago [-]
I am not convinced that Turbovec yields better retrieval than the same amount of bits of a Matryoshka embedding.
sp1982 7 hours ago [-]
If anyone is looking to retrofit to an existing pipeline, I use similar ideas to compress vectors for job search, getting roughly 8x compression with about a 3.5% drop in quality. My experiment: https://corvi.careers/blog/vector-search-embedding-compressi...
spoaceman7777 6 hours ago [-]
Well. That is insane. O_O Fantastic job!
burgerboii 8 hours ago [-]
Who is this co-author called t <t@t>?
cute_boi 5 hours ago [-]
As it is heavily vibe coded, I think member of technical staff at antropic has no clue....
Next Prompt: remove t@t and force commit.
esafak 8 hours ago [-]
lancedb and duckdb integrations would be great...
zuzululu 8 hours ago [-]
what could i use this for as part of my agentic workflow? codebase indexing? docs ?
kyxsc 8 hours ago [-]
notes/docs/wiki is a great use case
cute_boi 5 hours ago [-]
Another vibe coded slop where they can't even spend time on Readme or documentation around code...
refulgentis 6 hours ago [-]
Bloviating nonsense, 3rd time I’ve seen something like this in HN since TurboQuant came out. You don’t need float32, never did. Source: I’ve been writing on device embedding code for 4 years.
https://ann-benchmarks.com/index.html https://vector-index-bench.github.io/ https://big-ann-benchmarks.com/neurips23.html
It's been a while, but I do recall some high-performing vector matching indexes being very large.
There's an oxirs-wasm with RDF and SPARQL bindings with a query budget. Tantivy-wasm says that the release WASM bundle is 1.5 MB.
cool-japan/oxirs: https://github.com/cool-japan/oxirs
oxirs-wasm: https://crates.io/crates/oxirs-wasm
tantivy-wasm: https://github.com/phiresky/tantivy-wasm
Is there an advantage to adding an MCP local memory interface over agent instructions on how to use a rust CLI?
And then write Markdown documents with Google OKF-like frontmatter YAML metadata for agents that work with tokens not linked data graphs; https://github.com/GoogleCloudPlatform/knowledge-catalog/blo...
Next Prompt: remove t@t and force commit.