RetrievalModels class abstract final

Verified official models accepted by UniversalEmbedderOptions.

Google's EmbeddingGemma 2 models with a vision encoder, as its Universal Embedder guide lists them, from Google's LiteRT community on Hugging Face, Apache 2.0, pinned to their revisions. Both embed into 768 dimensions. Google's engine refuses the text-only EmbeddingGemma 2 (270M) for this task: "tf_lite_vision_encoder not found in the model".

Properties

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Constants

byName → const Map<String, DownloadAsset>

Every model above by the name an app lists to bundle it, under hooks.user_defines.mediapipe_retrieval.models in pubspec.yaml.

embeddingGemma2 → const DownloadAsset

EmbeddingGemma 2, text, images and audio, 740M parameters: 485 MB.

embeddingGemma2TextVision → const DownloadAsset

EmbeddingGemma 2, text and images, 440M parameters: 388 MB. The model the gallery runs.