A pluggable embedding backend (LiteRT C API + Gecko/EmbeddingGemma, ONNX,
or a third-party backend). Same probe-chain shape as
InferenceEngineProvider: selected by probing the embedding model spec,
highest-priority first match.
Passed to FlutterEdgeAi.initialize via embeddingBackends:. A backend
only DESCRIBES what to run (describe); core builds, hosts, validates and
closes the model, so every engine gets the same request checks and the
same close semantics.
Extend it (final class MyBackend extends EmbeddingBackendProvider);
base, so it cannot be implemented and a member added later reaches every
backend through its superclass.
Constructors
- EmbeddingBackendProvider()
-
const
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- name → String
-
Human-readable name for diagnostics / error messages.
no setter
- priority → int
-
Selection precedence on overlap. Core backends use 0.
no setter
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
canHandle(
EmbeddingModelSpec spec) → bool -
Whether this backend can serve
spec. Probed by the registry. -
describe(
EmbeddingModelSpec spec, RuntimeConfig config) → Future< EmbeddingPassDescriptor< Object> > -
A pure description of what to run for
specwithconfig. -
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