CachedLLMProvider class

A wrapper that adds caching capability to any LLM provider.

This decorator pattern allows transparent caching of LLM responses without modifying the underlying provider implementations.

Implemented types

• LLMProvider

Constructors

CachedLLMProvider({required LLMProvider delegate, required LLMCache cache})

Creates a cached wrapper around an existing provider.

Properties

availableModels → List<String>

List of model names available from this provider.

no setter, override

defaultModel → String

The default model to use if none is specified.

no setter, override

hashCode → int

The hash code for this object.

no setter, inherited

name → String

Human-readable name of this provider (e.g., "OpenAI", "Claude").

no setter, override

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

stats → Map<String, dynamic>

Returns cache statistics for this provider.

no setter

Methods

generateResponse(String prompt, {List<String>? context}) → Future<String>

Generates a response from the LLM based on the given prompt.

override

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