InMemoryVectorStore class
A simple, local, list-backed Vector Store.
Automatically generates embeddings using the provided AIProvider and performs brute-force cosine similarity searches in runtime memory. Suitable for small-scale RAG on device without external dependencies.
- Implemented types
Constructors
- InMemoryVectorStore({required AIEmbeddingProvider embedder})
Properties
-
documents
→ List<
AIDocument> -
Returns all currently stored documents.
no setter
- embedder → AIEmbeddingProvider
-
The provider used to generate text embeddings.
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
addDocuments(
List< AIDocument> docs) → Future<void> -
Adds documents to the store.
Implementation should compute embeddings if the document doesn't have them yet.
override
-
clear(
) → Future< void> -
Deletes all documents in this store.
override
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
similaritySearch(
String query, {int limit = 4}) → Future< List< AIDocument> > -
Searches for the most similar documents to the given query.
override
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited