emmyoh/zebra
A vector database for querying meaningfully similar data.
Zebra helps you manage and query large collections of complex data like documents, images, or audio by finding items that are meaningfully similar to each other. You input your data, and it helps you retrieve related content without requiring the entire dataset to be loaded into memory. This is ideal for developers building content recommendation systems or other applications that need to find semantically similar items.
No commits in the last 6 months.
Use this if you are building an application that needs to find semantically similar data (like recommendations) from a large, evolving dataset, and you require efficient on-disk storage, safe multithreaded access, and the ability to add and remove items without significant downtime or memory spikes.
Not ideal if your application requires extremely precise 'nearest' neighbor results over 'close enough' similarities, or if your dataset is static and small enough to be loaded entirely into memory, as other solutions might offer higher recall in those specific scenarios.
Stars
16
Forks
—
Language
Rust
License
AGPL-3.0
Category
Last pushed
Mar 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/emmyoh/zebra"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
databendlabs/databend
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from...
oceanbase/oceanbase
The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.
matrixorigin/matrixone
MySQL-compatible HTAP database with Git for Data, vector search, and fulltext search....
ArcadeData/arcadedb
ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB...
datalevin/datalevin
A simple, fast and versatile Datalog database