hyperDB
hyperDB copied to clipboard
A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.
We need features like cloud deployment, access management, data compliance, etc Then we can easily markup the valuation to $100M
This will directly increase the public VC interest because the code is more compact and robust.
Are you considering adding K8 support for easier deployments to Cloud services?
Subtle suggestion to rebrand the "entire" package with the name HyperB(etter)S(earch). I feel This better reflects the potential of Hyper !
I've heard rumors of traditional nlp techniques used by tribal elders that are able to achieve knowledge representations *without even using deep learning*. The techniques even sound magical, with names...
In all seriousness, how does this compare to FAISS?
Will you add support for LLAMA? 🦙 embeddings are not normalized to unit length like the OpenAI embeddings, meaning you can both represent direction and magnitude.
openai.error.AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = ', or you can set the environment variable OPENAI_API_KEY=). If your API key is...
Changed: - Added search by vector - Don't save on empty doc or vector - if there is no vector to search return an empty list