discontinuedPackage flutter_gemma_embeddings has been discontinued.

➡️ Moved to flutter_edge_ai_embeddings

flutter_gemma_embeddings has moved to flutter_edge_ai_embeddings, part of Flutter Edge AI. This is the final release under the old name; new versions, features and fixes ship as flutter_edge_ai_embeddings.

To migrate, replace the flutter_gemma_embeddings dependency with flutter_edge_ai_embeddings, change imports from package:flutter_gemma_embeddings/flutter_gemma_embeddings.dart to package:flutter_edge_ai_embeddings/flutter_edge_ai_embeddings.dart, and run dart fix --apply. Installed models and app data carry over. See the migration guide.

The documentation below describes the last flutter_gemma_embeddings release.

Libraries

embedding_tokenizer
Public, native-only export of the Gemma SentencePiece EmbeddingTokenizer adapter (loadGemmaSentencePieceEmbeddingTokenizer, loadEmbeddingTokenizer, encodeForEmbedding) for native-only leaves that need to import it from a file that is itself native-only (never reached on web) — engine packages' embedding backends (e.g. flutter_gemma_litertlm's LiteRtEmbeddingBackend).
flutter_gemma_embeddings
The embedding tokenizers for flutter_gemma.
tokenizer_convention
Public export of the tokenizer.json convention reader, for engine packages that route a tokenizer file to an adapter and need to know which convention the file declares before building anything.
wordpiece_embedding_tokenizer
Public, native-only export of WordPieceEmbeddingTokenizer for native-only leaves that need to import it from a file that is itself native-only (never reached on web) — engine packages' embedding backends (e.g. flutter_gemma_onnx's ONNX tokenizer loader, which sniffs a tokenizer.json and routes to either this WordPiece adapter or the Gemma SentencePiece one in embedding_tokenizer.dart).