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 5 hours ago [-]
Also the removal latency is on a log scale. Which is quite insane.
nharada 5 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 4 hours ago [-]
Anthropic employee. This is what your brain on kool aid looks like
deeviant 4 hours ago [-]
Then again, if the only thing the human doing is bitching about AI use, it's not really that comparatively useful.
anishvarghese 5 hours ago [-]
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?
coredog64 3 hours ago [-]
Can WASM use AVX512-VNNI?
LtdJorge 2 hours ago [-]
No, WASM only has 128b SIMD instructions, for now.
westurner 4 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.
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 4 hours ago [-]
Well. That is insane. O_O Fantastic job!
tracespect 1 hours ago [-]
açıkçası rust dilini öğrenmeyi ve kendimi eğitmeyi çok istiyorum.
burgerboii 5 hours ago [-]
Who is this co-author called t <t@t>?
cute_boi 2 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.
zuzululu 5 hours ago [-]
what could i use this for as part of my agentic workflow? codebase indexing? docs ?
kyxsc 5 hours ago [-]
notes/docs/wiki is a great use case
esafak 5 hours ago [-]
lancedb and duckdb integrations would be great...
refulgentis 3 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.
cute_boi 2 hours ago [-]
Another vibe coded slop where they can't even spend time on Readme or documentation around code...
https://ann-benchmarks.com/index.html https://vector-index-bench.github.io/ https://big-ann-benchmarks.com/neurips23.html
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.