TL;DR
Zvec is a lightweight, in-process vector database developed by Alibaba, designed to be embedded directly into applications for fast similarity search without requiring a separate server.
Key features
Blazing Fast: Searches billions of vectors in milliseconds.
Simple, Just Works: Install and start searching in seconds. Pure local, no servers, no config.
Dense + Sparse Vectors: Support dense and sparse embeddings, multi-vector queries, and a rich selection of vector index types.
Full-Text Search (FTS): Native keyword-based full-text search on string fields.
Hybrid Search: Combine vector similarity, full-text search, and structured filters in a single query.
DiskANN Index: On-disk index that reduces memory usage for large-scale datasets.
Multiple SDKs: Python, Node.js, Go, Rust SDKs available.
When to use it
Ideal for applications requiring similarity search on vector embeddings, especially when lightweight local deployment or serverless environments are needed. It is production-tested within Alibaba Group, making it suitable for reliability-critical use cases.