zvec v0.7.0

A lightweight, lightning-fast, in-process vector database

Release notes

## 🚀 Zvec v0.7.0 Release Notes

### ⚠️ Breaking Changes
+ **C++ public API switched to snake_case:** All public C++ SDK interfaces (`Index`, `Collection`, etc.) have been moved from PascalCase to snake_case. For example, `Open()` → `open()`, `Search()` → `search()`, `Query()` → `query()`, and `Insert()` → `insert()`. C++ SDK users will need to update their call sites when upgrading. The C API and Python API names remain unchanged. ([#683](https://github.com/alibaba/zvec/pull/683))

### 📦 New Features
+ **IVF RaBitQ index:** Added RaBitQ quantization support for IVF indexes, extending RaBitQ to more dense-vector retrieval scenarios. C and Python bindings and test coverage are included. ([#540](https://github.com/alibaba/zvec/pull/540))
+ **Turbo preprocessor framework:** Introduced an optional preprocessor component in the Turbo quantizer module. Fast Hadamard Transform (FHT) rotation is implemented now, with OPQ rotation and dimensionality reduction planned for future releases. ([#548](https://github.com/alibaba/zvec/pull/548))
+ **Turbo PQ-INT8 quantizer:** Added a PQ-based INT8 quantizer in the Turbo framework, covering L2, Cosine, and Inner Product distance metrics for users who need higher compression. ([#554](https://github.com/alibaba/zvec/pull/554))
+ **Turbo record quantizers:** Migrated INT8/INT4 record quantization and FP16 quantizers into the Turbo framework, added portable scalar distance kernels for non-SIMD targets, and reworked the kernel dispatch registry so every quantization type maps to one explicit backend path. ([#624](https://github.com/alibaba/zvec/pull/624))
+ **Uniform uint7/uint8 quantization:** Exposed uniform uint7 and added uniform uint8 quantization options, giving users more flexibility when trading recall against compression. ([#608](https://github.com/alibaba/zvec/pull/608))
+ **RaBitQ runtime AVX2/AVX512 dispatch:** HNSW-RaBitQ now selects AVX2 or AVX512 implementations at runtime based on the host CPU, removing the need to hard-code an instruction set at build time. ([#632](https://github.com/alibaba/zvec/pull/632))
+ **DiskANN cross-platform support:** DiskANN was extended from Linux x86_64 to Linux ARM64 and macOS ARM64 (Apple Silicon). It now selects the best available I/O backend — io_uring, libaio, or pread — and falls back safely. macOS uses `F_NOCACHE` and disables read-ahead for DiskANN files. ([#557](https://github.com/alibaba/zvec/pull/557), [#599](https://github.com/alibaba/zvec/pull/599))
+ **Vamana two-pass graph build:** Added an optional two-pass graph build path for Vamana, improving graph quality on some datasets. ([#634](https://github.com/alibaba/zvec/pull/634))
+ **HNSW graph build from original vectors:** HNSW can now build the graph from raw, original vectors supplied by a provider while search still runs against the vectors stored in the index, improving graph quality when stored vectors are lossy. ([#657](https://github.com/alibaba/zvec/pull/657))
+ **FTS ngram tokenizer:** Added an ngram tokenizer for full-text search, useful for character-level matching such as short text, code, or pinyin. ([#593](https://github.com/alibaba/zvec/pull/593))
+ **DocIterator for full collection traversal:** Added `DocIterator` for streaming full-collection traversal across C++, C, and Python. The iterator takes a snapshot, so later writes and deletes are invisible, and the Python API supports `with collection.iter_docs()`. ([#597](https://github.com/alibaba/zvec/pull/597))
+ **musllinux wheels:** Added x86_64 and arm64 Python wheel builds for musl libc environments, plus compatibility fixes for musl thread stacks, logger singleton lifetime, and DiskANN heap over-reads. ([#649](https://github.com/alibaba/zvec/pull/649))
+ **Prebuilt SDK release pipeline (pending merge):** PR [#628](https://github.com/alibaba/zvec/pull/628) proposes a GitHub Release pipeline that builds and publishes prebuilt C/C++ SDK packages for Linux (glibc and musl, x86_64 and arm64), macOS ARM64,…

Share this resource