mediapipe_retrieval 0.1.3

Google's MediaPipe retrieval tasks for Flutter: Universal Embedder, one embedding space for text, images and audio, and Semantic Retriever, an on-device vector index over them.

0.1.3

• The README has an installation section using flutter pub add.
• With mediapipe_core 0.1.3, downloads of models and native libraries wait out short network failures.

0.1.2

Release 0.1.2.

0.1.1

Adds Google's NOTICE at the package root.

0.1.0

The first release.

• Universal Embedder and Semantic Retriever on Android, iOS, macOS, Linux, Windows and the web, through Google's official MediaPipe runtimes: its per-family 1.2.0 retrieval C library natively and @mediapipe/tasks-retrieval in browsers.
• Universal Embedder and Semantic Retriever need 64-bit Android: 32-bit (armeabi-v7a) cannot hold their models, and their capability queries say so.
• UniversalEmbedder embeds text, encoded images and audio samples into one space, with cosineSimilarity; SemanticRetriever indexes documents, images, audio and mixed content with metadata and retrieves the nearest records, with the same results on every platform.
• RetrievalModels pins Google's EmbeddingGemma 2 models.
• Neither task is offered in WebKit, where Google's browser runtime returns zeros for every input with both models (UP-054).