alibaba /zvec
A lightweight, lightning-fast, in-process vector database
★ 16,244⑂ 1,022👁 70⑃ 675● 200▤ 16
+3
Daily
16,244
stars
1,022
forks
70
watchers
675
prs
200
issues
16
releases
README
English | 中文
🚀 Quickstart |
🏠 Home |
📚 Docs |
📊 Benchmarks |
🔎 DeepWiki |
🎮 Discord |
🐦 X (Twitter)
Zvec is an open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Battle-tested within Alibaba Group, it delivers production-grade, low-latency and scalable similarity search with minimal setup.
[!Important]
🚀 v0.8.0
- Broader platform support: Added Intel Mac and Windows ARM64 builds, wheels, and SDKs; extended DiskANN to Windows, Android, and iOS, and RaBitQ to Windows x86_64.
- Chinese FTS ready to use: Embedded the default Jieba dictionary and HMM model, so Chinese tokenization needs no separate dictionary files or path configuration.
- Lower index build costs: Reduced peak memory during IVF / DiskANN builds and merges, and accelerated HNSW RaBitQ construction through vector reuse and batched lookups. Build and nested training tasks now enforce configured thread limits more strictly.
- Faster distance computation: Extensively refactored quantizers and distance calculations to benefit multiple
quantization types and metrics, with major improvements to INT4 kernels and Linux ARM64 performance.
- Faster search: Added faster Uniform quantizers and optimized Vamana graph layout and prefetching. Uniform quantization avoids per-point score reconstruction, though a shared min/max range can increase quantization error and reduce recall.
- Bug fixes and improvements: Added more flexible UTF-8 document IDs up to 1,024 bytes; fixed concurrent reads during segment switches, index rebuilding with deleted rows, and correctness issues in LIKE and floating-point range filters.
👉 Read the Release Notes
[^query-performance]: Measured on GIST 1M with L2 distance, INT8 quantization, and HNSW on a 16-core Linux ARM64 system.
💫 Features
- Blazing Fast: Searches billions of vectors in milliseconds.
- Simple, Just Works: Install and start searching in seconds. Pure local, no servers, no config, no fuss.
- Dense + Sparse Vectors: Support dense and sparse embeddings, multi-vector queries, and a rich selection of vector index types that scale from memory to disk.
- Full-Text Search (FTS): Native keyword-based full-text search — query string fields with natural-language or structured expressions.
- Hybrid Search: Fuse vector similarity, full-text search, and structured filters in a single query for precise results.
- Durable Storage: Write-ahead logging (WAL) guarantees persistence — data is never lost, even on process crash or power failure.
- Concurrent Access: Multiple processes can read the same collection simultaneously; writes are single-process exclusive.
- Runs Anywhere: As an in-process library, Zvec runs wherever your code runs — notebooks, servers, CLI tools, or even edge devices.
📦 Installation
Zvec offers official SDKs across multiple languages:
| SDK | Install / Dependency | Source |
| --- | --- | --- |
| Top issues
#868[Performance]:High-selectivity range filter materializes a full bitmap — `bitset_set_list` ~49% CPU, dwarfing the ANN search12 comments · 2026-11-02#586[Feature]:未来是否会支持单写多读(一个写进程 + 多个只读进程)?4 comments · 2026-07-10#293clang-tidy: enable bugprone-*4 comments · 2026-03-31#781Bug: Collection.group_by_query returns empty results with ID-out-of-range errors (UINT64_MAX)3 comments · 2026-09-24#291clang-tidy: enable performance-*3 comments · 2026-03-31#791[Bug]: Document with NULL in a nullable vector column makes filter-only scans fail when include_vector=true ("fetch vector failed: Failed to fetch vector from index")2 comments · 2026-09-29#789Durability: acknowledged data can be lost after power loss, and a damaged manifest can make recovery delete every segment2 comments · 2026-09-28#784[Bug]: ID map RocksDB is never compacted; ascending primary keys leave one SST and one open fd per flush2 comments · 2026-09-25
Discussions
#767I used zvec in my project (coding agent memory)0 comments · 2026-09-17#506Is embedding zvec considered in the roadmap?1 comments · 2026-06-19#505Different between Zvec and SQLite Vector1 comments · 2026-06-18#313v0.3.00 comments · 2026-04-03#310🗳️ Community Feedback: What should we build next for Zvec?3 comments · 2026-04-03#161Build for Windows1 comments · 2026-02-23#158Try to install using pip and npm1 comments · 2026-02-23#154Proposal: Standalone DuckDB Extension for zvec0 comments · 2026-02-20
Latest release
v0.8.1 v0.8.1 2026-11-06🚀 Zvec v0.8.1 Release Notes 📦 New Features + PQ for HNSW and IVF: Added PQ4/PQ8 and optional OPQ, covering training, search, persistence, and subsequent updates. (833) + Broader platform support: Enabled RaBitQ on Linux, macOS, Android, and iOS ARM64, plus Intel Mac. DiskANN now supports Intel Mac and Windows ARM64. (832, 874) + Grouped search in the C API: Added grouped vector query and result-management APIs. (845) 🚀 Performance Improvements + Lower build memory: Reduced vector copying and temporary storage in DiskANN, IVF, and selected HNSW construction paths. (853, 877, 879, 88