GemmaRag class

RAG (retrieval-augmented generation) operations, reached via FlutterGemma.rag. Thin, stateless delegator over the vector store; opt-in (see FlutterGemma.rag). Modelled as a single const instance purely to give the operations a rag. namespace on the facade — it holds no state and is not itself a test seam. To fake RAG in tests, substitute FlutterGemmaPlugin.instance (which every method here delegates to).

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

addDocument({required String id, required String content, String? metadata}) Future<void>
Add a document; its embedding is computed automatically (needs an active embedding model).
addDocumentWithEmbedding({required String id, required String content, required List<double> embedding, String? metadata}) Future<void>
Add a document with a precomputed embedding.
clear() Future<void>
Remove all documents from the vector store.
initialize(String databasePath) Future<void>
Initialize the vector store database.
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
removeDocument({required String id}) Future<void>
Remove a single document by ID. No-op if the ID is absent.
searchSimilar({required String query, int topK = 5, double threshold = 0.0, Filter? filter}) Future<List<RetrievalResult>>
Search for similar documents. filter constrains by declared payload fields (see FlutterGemmaPlugin.searchSimilar).
stats() Future<VectorStoreStats>
Vector store statistics.
toString() String
A string representation of this object.
inherited

Operators

operator ==(Object other) bool
The equality operator.
inherited