maxMarginalRelevanceSearch method

Future<List<Document>> maxMarginalRelevanceSearch({ required String query, VectorStoreMMRSearch config = const VectorStoreMMRSearch(), })

Returns docs selected using the maximal marginal relevance algorithm (MMR) for the given query.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

• query is the query to search for.
• config the configuration for the search.

Implementation

Future<List<Document>> maxMarginalRelevanceSearch({
  required final String query,
  final VectorStoreMMRSearch config = const VectorStoreMMRSearch(),
}) async {
  return maxMarginalRelevanceSearchByVector(
    embedding: await embeddings.embedQuery(query),
    config: config,
  );
}