MemoryVectorStore constructor

MemoryVectorStore({ required Embeddings embeddings, double similarityFunction(List<double> a, List<double> b) = cosineSimilarity, List<MemoryVector>? initialMemoryVectors, })

Main constructor for MemoryVectorStore.

• embeddings is the embeddings model to use to embed the documents.
• similarityFunction is the similarity function to use when comparing vectors. By default, it uses cosine similarity.
• initialMemoryVectors is an optional list of MemoryVector to initialize the vector store with. This is useful when loading a vector store from a database or file.

If you want to create and populate a MemoryVectorStore from a list of documents or texts, use MemoryVectorStore.fromDocuments or MemoryVectorStore.fromText.

Implementation

MemoryVectorStore({
  required super.embeddings,
  this.similarityFunction = cosineSimilarity,
  final List<MemoryVector>? initialMemoryVectors,
}) : memoryVectors = [...?initialMemoryVectors];