zeppelin-embed 0.2.0

In-process vector, lexical, and hybrid search for macOS and Apple silicon

Coverage
100%
2784 out of 2784 items documented0 out of 933 items with examples
Size
Source code size: 5.9 MB This is the summed size of all the files inside the crates.io package for this release.
Documentation size: 37.6 MB This is the summed size of all files generated by rustdoc for all configured targets
Ø build duration
this release: 15s Average build duration of successful builds.
all releases: 23s Average build duration of successful builds in releases after 2024-10-23.
Links
Homepage
zepdb/zeppelin-embed
3 0 0
crates.io
Dependencies
Versions
Owners

Zeppelin Embed

Zeppelin Embed is the fastest and most accurate in-process search engine built for macOS and Apple silicon. It stores vectors, text, metadata, and search indexes in one persistent directory and supports vector, lexical, and hybrid retrieval through a native Rust API.

cargo add zeppelin-embed

Applications provide their own document and query vectors. The engine owns the persistent store, append-only ingestion, point-in-time snapshots, filtering, and retrieval.

Run the bundled example after cloning the repository:

cargo run --release -p zeppelin-embed --example five_vectors_search

See the project README for benchmark results, storage details, and the complete native API quickstart.

Licensed under GPL-3.0-only.