beernet12 minutes ago
Why not just use Qdrant? They've been integrating TurboQuant for months, works well.
ghm21992 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!
ghm21992 hours ago
Also the removal latency is on a log scale. Which is quite insane.
nharada2 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
badatnamesan hour ago
Anthropic employee. This is what your brain on kool aid looks like
deeviantan hour ago
Then again, if the only thing the human doing is bitching about AI use, it's not really that comparatively useful.
anishvarghese2 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?
cpursley2 hours ago
Also interested.
westurneran hour 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.
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...
sp19822 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...
spoaceman7777an hour ago
Well. That is insane. O_O Fantastic job!
burgerboii2 hours ago
Who is this co-author called t <t@t>?
refulgentis24 minutes 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.
zuzululu2 hours ago
what could i use this for as part of my agentic workflow? codebase indexing? docs ?
kyxsc2 hours ago
notes/docs/wiki is a great use case
esafak2 hours ago
lancedb and duckdb integrations would be great...