[GitHub Trending] RyanCodrai/turbovec
6.9 relevance
Score Breakdown
technical depth 8
novelty 7
actionability 7
community 5
strategic 5
personal 7
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Rust-based vector index with Python bindings is technically deep and relevant to AI/ML infrastructure.
Summary
turbovec is a Rust vector index with Python bindings that compresses a 10M-document corpus from 31 GB (float32) to 4 GB using Google Research's TurboQuant algorithm, a data-oblivious quantizer matching the Shannon lower bound without training. It outperforms FAISS IndexPQFastScan by 12–20% on ARM via hand-written NEON kernels and matches it on x86 with AVX-512BW, while supporting online ingest, filtered search with SIMD-aware allowlists, and drop-in replacements for LangChain, LlamaIndex, Haystack, and Agno vector stores.
Author
RyanCodrai