zvec
Zvec is a vector database that runs in-process, which can be directly embedded in applications. It offers hybrid search capabilities with intensive and sparse vector support; it provides disk-based storage and data permanence with the WAL mechanism. Developed with C++, this library offers extensive SDK support for different platforms.
zvec
95alibaba · Search Engines
Common commercial products in this category: Algolia, Elastic Cloud, Azure AI Search
- Embedded in your application, you can search for low-latency vector similarity.
- You can run hybrid queries by combining vector search and full text search.
- With disk-based storage and WAL support, you can protect your data against process crashes.
- ↑ PositiveHacker News
Zvec: A lightweight, fast, in-process vector database
“Just put Zvec vs LanceDB vs Qdrant through the paces on a 3 collection (text only) 10k per collection dataset. Average latency across ~500 queries per collection per database: Qdrant: 21.1ms LanceDB: 5.9ms Zvec: 0.8ms Both Qdrant and LanceDB are running with Inverse Document…”
- • NeutralHacker News
Zvec: A lightweight, fast, in-process vector database
“Author here. Thanks for putting Zvec through its paces and sharing such detailed results—really appreciate the hands-on testing! Just a bit of context on the storage behavior: Zvec currently uses memory-mapped files (mmap) by default, so once the relevant data is warmed up in…”
My note
Alternative pages
More in: Search Engines
- Meilisearch★ 59,725 · yesterday
- ZincSearch★ 17,927 · 1 mo ago
- xerj★ 17,772 · today
- Tantivy★ 16,368 · yesterday
- OpenSearch★ 13,937 · today
- flexsearch★ 13,815 · 4 mo ago