Haven't had great results with the AI portion though, even with the recommended model. Embeddings seem really poor, and has lots of misses and false positives.

Given how good the new multimodal models are, I've been thinking it would be much better to just have a multimodal model describe the image, and let the searching be done by the already included melleisearch.

That said, due to reasons I haven't had time to mess with it past couple of months, so perhaps something drastic has changed.