flutter_gemma_interface library

Classes

EmbeddingModel: Represents an embedding model instance.
FlutterGemmaPlugin: Low-level platform-interface tier (the federated-plugin SPI) for flutter_gemma. It hosts the abstract runtime types (InferenceModel, InferenceModelSession, InferenceChat, EmbeddingModel, SpeechRecognizer, SpeechSynthesizer, …) and the platform-dispatch singleton instance.
InferenceModel: Represents an LLM model instance.
InferenceModelSession: Session managing response generation from the model.
SessionMetrics: Session metrics containing token usage and performance statistics.
SpeechRecognizer: Represents a speech-to-text model instance.
SpeechSynthesizer: Represents a text-to-speech model instance.

TaskType: Task type for embedding generation, following Google RAG SDK convention.

RawSdkResponseSession: Mixin for sessions that surface the SDK's structured raw JSON response (LiteRT-LM Gemma 4 path with tool_calls). Allows InferenceChat to read the structured tool calls without a hard dependency on a concrete session type, and lets non-FFI sessions opt out by simply not implementing this mixin.