We'll move to Firebase Vertex AI. We can also take advantage of Google ML Kit https://pub.dev/packages/google_ml_kit for several features: * [Image Labeling](https://developers.google.com/ml-kit/vision/image-labeling) for generating tags for image modalities for later RAG filtering - Similarly [Object Detection and Tracking](https://developers.google.com/ml-kit/vision/object-detection) can be also used for extracting tags * [Language Identification](https://developers.google.com/ml-kit/language/identification) could be an option for typing inputs (when the app is used not in a voice assistant mode but typing #55) * [On-Device Translation](https://developers.google.com/ml-kit/language/translation) can be an off-line option for translation * [Smart Reply](https://developers.google.com/ml-kit/language/smart-reply) could also be used for completion when the app is used in typing mode #55 * [Entity Extraction](https://developers.google.com/ml-kit/language/entity-extraction) can be used for tag generation for textual inputs or transcribed modalities
We'll move to Firebase Vertex AI. We can also take advantage of Google ML Kit https://pub.dev/packages/google_ml_kit for several features: