CloseVector is a vector database with libraries for browsers & node.js. Prioritizing easy integration & scalability, its vector index runs on the user's machine for optimal performance.
We're pleased to present the alpha release of CloseVector, a portable vector database designed with machine learning applications in mind. If you've been considering building an app that interacts with articles or PDFs, or if you're in need of a recommendation system for limited candidates, we hope CloseVector can be a potential solution for you.
For more information, checkout: https://closevector-docs.getmega...
By the way, CloseVector is compatible with LangChain, offering classes that extend the SaveableVectorStore from LangChain. You can easily integrate CloseVector into your LangChain apps.
@blaise123 Thank you; I am flattered. While we recommend using your own embeddings service, we offer a proxied OpenAI embeddings API (https://closevector-docs.getmega...) for those aiming to rapidly integrate with a vector database. This API has usage limits based on frequency and the number of tokens used per day. We have not set a specific threshold, as I believe a threshold determined by the 90th percentile would be suitable. However, we currently lack sufficient data to finalize that decision. For your convenience, both classes and a demo can be found here (https://github.com/MegaPortal/cl...).
CloseVector
CloseVector
PreCog by UbikAI
CloseVector
PreCog by UbikAI