BackendMultimodalSupport class abstract
Optional backend capability for multimodal projectors.
LlamaEngine projector loads throw LlamaUnsupportedException on a
backend without it, and the engine reports vision and audio input from
BackendDirectMediaInput alone. A backend whose support depends on its
runtime implements it and throws LlamaUnsupportedException or
UnsupportedError from a call that runtime cannot run.
Constructors
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
multimodalContextCreate(
int modelHandle, String mmProjPath) → Future< int?> -
Loads the multimodal projector at
mmProjPathformodelHandleand returns its handle. -
multimodalContextFree(
int mmContextHandle) → Future< void> -
Frees the projector
mmContextHandle. -
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
supportsAudio(
int mmContextHandle) → Future< bool> -
Whether the projector
mmContextHandletakes audio input. -
supportsVision(
int mmContextHandle) → Future< bool> -
Whether the projector
mmContextHandletakes image input. -
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited