Thanks for asking. The privacy filter was actually one of the first things we’ve launched with: Omnifact's privacy filter leverages a custom-trained Named Entity Recognition (NER) model for advanced data masking and context-aware content filtering. This ensures sensitive information is replaced with placeholders while preserving the AI's contextual accuracy. The platform supports on-premise deployment and self-hosted LLMs, offering full data control and compliance with regulatory standards.
On one index I'm using OPQ16_64,IVF262144_HNSW32,PQ16 with 128 dimensions initially.
1024 dimensions is a lot! Could you elaborate on what application requires that many? If it's a DNN layer output, your data must be sparse, so dimensionality reduction won't affect your recall if tuned properly.
It's actually a DNN layer output. I haven't considered dimensionality reduction, yet. Thanks for pointing my there, I'll look into it. Probably thats the better way to go.
or you just don’t have to invent the oven, the overall ingredients and how to make a dough, but still need to learn how to get from the basic ideas to something tasty which you want to show to the world...
It works surprisingly well on my old iPad Pro! Thank you for building this. Sure, many tools that require additional privileges (and some syscalls?) do not work, but i’d love to see more progress here. Having a local linux shell on my iPad would be a game changer for me.
