Indexes and searches embeddings with 2- to 4-bit TurboQuant compression in a Rust library with Python bindings, for local RAG pipelines that need a small memory footprint.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Call the API
Auth None needed
Its page: github.com/RyanCodrai/turbovec
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- API
- Auth
- None
- Skills
- 3
Skills
Filtered Search
Restricts search() to an id allowlist or slot bitmask inside the kernel, returning up to k results from the allowed set without over-fetching.
Incremental Saves
Persists only what changed since the last sync(path) call with one fsync, so small appends or removals stay fast on large indexes.
Framework Integrations
Replaces the in-memory vector stores of LangChain, LlamaIndex, Haystack and Agno through optional pip extras such as turbovec[langchain].