clawhdf5 committer agentandClaude Sonnet 5
377c8b6f17
CI / test (pull_request) Canceled after 0s
The SIMD migration weakened the near-zero-norm guard in all four clawhdf5-accel cosine_similarity backends (scalar/avx2/avx512/neon) from `denom < f32::EPSILON` to `denom == 0.0`. Vectors with a tiny but nonzero norm (denom in (0, 1.19e-7)) fell through to dot/denom and scored as identical instead of maximally dissimilar, diverging from the pre-SIMD scalar loop's documented fallback behavior. Restores the epsilon threshold in all four backends so `1.0 - cosine_similarity(...)` in hnsw.rs::compute_distance reproduces the old fallback exactly. Adds regression tests in clawhdf5-accel and clawhdf5-ann locking in the near-zero-norm case. Co-Authored-By: Claude Sonnet 5 <[email protected]>
clawhdf5-ann
HNSW approximate nearest neighbor index stored as HDF5.
Features
- Build and query HNSW indexes persisted in HDF5 format
- Pure Rust, no C dependencies
- Efficient similarity search for high-dimensional vectors
Usage
use clawhdf5_ann::HnswIndex;
let index = HnswIndex::from_hdf5("vectors.h5").unwrap();
let neighbors = index.search(&query, 10);
License
MIT