Vibe Coding Discoverturbovec
View on GitHubA vector index built on TurboQuant, written in Rust with Python bindings
turbovec is a Rust vector index with Python bindings built on Google's TurboQuant quantizer. It offers online ingest with no training step, SIMD-accelerated search reported faster than FAISS FastScan, allowlist-filtered search, and incremental crash-safe saves.
Use Cases
Local/private RAG over large corpora with reduced RAMMemory-efficient vector index as a FAISS IndexPQ replacementHybrid retrieval by passing a SQL/BM25/ACL allowlist into searchIncremental crash-safe persistence of an in-process vector indexStable external uint64 ids with O(1) deletes for document storesDrop-in vector store behind LangChain, LlamaIndex, Haystack, Agno pipelinesAir-gapped embedding search paired with open-source embedding modelsLow-latency ANN search on ARM (NEON) and x86 (AVX-512) CPUs
Built With
- Language
- Rust
- Frameworks
- LangChain · LlamaIndex · Haystack · Agno · NumPy
Tags
vector-search · ann · quantization · embeddings · rust · python · simd · avx512 · neon · rag · faiss · nearest-neighbor · filtered-search · local-first · incremental-persistence · turboquant