DesktopInferenceModelSession class
Desktop implementation of InferenceModelSession.
Uses gRPC to communicate with the LiteRT-LM server. Buffers query chunks, images, and audio until getResponse is called.
Thread Safety: This session is NOT thread-safe. All method calls must originate from the same isolate. Concurrent access from multiple isolates may cause undefined behavior.
- Inheritance
-
- Object
- InferenceModelSession
- DesktopInferenceModelSession
Constructors
- DesktopInferenceModelSession({required LiteRtLmClient grpcClient, required ModelType modelType, required ModelFileType fileType, required bool supportImage, required bool supportAudio, required VoidCallback onClose})
Properties
- fileType → ModelFileType
-
final
- grpcClient → LiteRtLmClient
-
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- modelType → ModelType
-
final
- onClose → VoidCallback
-
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- supportAudio → bool
-
final
- supportImage → bool
-
final
Methods
-
addQueryChunk(
Message message) → Future< void> -
override
-
close(
) → Future< void> -
override
-
getResponse(
) → Future< String> -
override
-
getResponseAsync(
) → Stream< String> -
override
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
sizeInTokens(
String text) → Future< int> -
override
-
stopGeneration(
) → Future< void> -
override
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited