{"repo":"Project-Navi/ordvec","free":true,"listed":false,"github":"https://github.com/Project-Navi/ordvec","clone":"git clone https://github.com/Project-Navi/ordvec.git","description":"Training-free ordinal & sign quantization for compressed nearest-neighbour retrieval over high-dimensional embeddings. Pure Rust, zero system dependencies.","language":"Rust","stars":21,"topics":["ann","approximate-nearest-neighbor","embeddings","information-retrieval","nearest-neighbor","quantization","rust","simd","vector-database","vector-search"],"license":"Apache-2.0","category":"databases-storage","readme_excerpt":"ordvec Training-free ordinal & sign quantization for vector retrieval. ordvec is a small, pure-Rust crate for compressed nearest-neighbour search that quantizes the ordinal (rank) and sign structure of an embedding — no codebook, no learned rotation, no graph to build. Choose your surface You want to... Use Install --- --- --- Build retrieval in Rust ordvec cargo add ordvec@0.6 Build retrieval in Python ordvec python -m pip install ordvec Create or verify index manifests from Rust or a CLI ordvec-manifest cargo install ordvec-manifest Verify manifests from Python ordvec-manifest python -m pip install ordvec-manifest Quickstart: see a result in 30 seconds Python: Rust: Or add the dependency directly: The runnable Rust version is examples/quickstart.rs . Persist and reopen the same index without keeping the original float corpus: What is ordinal retrieval? Ordinal retrieval is a retrieval family where the index operates on order/sign quotients of embedding coordinates rather than metric magnitudes, with training-free compression, quotient-aware candidate generation, and asymmetric reranking against the original query signal. Dense retrieval assumes magnitude geometry is the primitive. Ordinal retrieval asks what survives when embeddings are quotiented down to coordinate order, signs, and relative salience. Surprisingly, enough retrieval signal survives to match dense qrel quality at much smaller storage, and those quotients support quotient-aware candidate-generation rules that","default_branch":null,"files":null,"tree":[],"storefront":"/r/Project-Navi","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Project-Navi/ordvec/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}