BackendChatPromptGeneration class abstract
Optional backend capability for a prompt that LlamaEngine.create
rendered from chat messages with media parts, as opposed to a prompt the
caller of LlamaEngine.generate wrote.
A backend that reads media placeholders in the prompt of
LlamaBackend.generate (<__media__>, <image>, <img> and the like)
would also read one that a chat message only quotes. With this interface
the engine hands such a backend the rendered prompt apart from a caller's.
Without it the engine passes the prompt to LlamaBackend.generate with
<__media__> where each part was and a zero-width space (U+200B) after
the first character of every other placeholder string.
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
-
generateChatPrompt(
int contextHandle, String prompt, GenerationParams params, {required String mediaMarker, List< LlamaContentPart> ? parts}) → Stream<List< int> > -
Generates like LlamaBackend.generate from the chat-rendered
prompt. -
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