Local vector database for Node.js with features similar to Pinecone but built using local files. Provides predictable local performance with full in-memory scans delivering sub-millisecond to low-millisecond latency for small/medium corpora.
Loading more......
On this page
Vectra
Vectra is a local vector database for Node.js with features similar to Pinecone but built using local files.
Each Vectra index is a folder on disk, with an index.json file in the folder that contains all the vectors for the index along with any indexed metadata.
Includes Pinecone-style filtering using a familiar subset of MongoDB query operators to filter by metadata before similarity ranking.
Full in-memory scans with pre-normalized cosine similarity deliver sub-millisecond to low-millisecond latency for small/medium corpora.
Since Vectra is file based, any language binding can be used to read or write a Vectra index, which means you can build a Vectra index using JavaScript and then read it using Python.
Vectra is intended to be used in scenarios where you have a small corpus of mostly static data that you'd like to include in your prompt, such as:
Vectra is available as an npm package and is open-source on GitHub.
Free and open-source.
Explore more items related to this one