Bridge between LlmRequest and one provider's HTTP API.
Extend this to add a provider. Subclasses should throw AdapterException on non-2xx responses and otherwise return whatever the model produced without judging it; validation and retries happen upstream.
It is a base class rather than an interface so that it can grow. A method
added here with a default body reaches every adapter without breaking it,
which is what lets planned work (streaming, sampling) land in a minor
release instead of a major one. Subclasses must themselves be base,
final or sealed.
- Implementers
Constructors
- LlmAdapter()
-
const
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
-
close(
) → void - Releases anything the adapter owns, typically the HTTP client it created when the caller did not supply one.
-
complete(
LlmRequest request) → Future< LlmResponse> -
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