Private offline AI search for docs, images, voice, videos

Re:Private offline AI search for docs, images, voice, videos by maltelandwehr on Tuesday November 11, 2025 @10:00AM (#45887987)

Looks interesting! Which LLM are you using under the hood?

[ Parent | on HN ]

Re:Private offline AI search for docs, images, voice, videos by c_guru on Tuesday November 11, 2025 @11:08AM (#45888957)

Thanks. For voice and video we use two-layered models (Whisper + fine-tuning), while for documents, images, and other content users can choose from multiple models. For example CLIP ViT-B/32, all-MiniLM-L6-v2, multilingual variants, etc. Everything runs fully offline.

[ Parent | on HN ]