Returns documents most similar to an embedding vector.
Embedded
Python SDK
JS/TS
similarity_search_by_vector( embedding: Union[List[ float ], np.ndarray], k: int = 4 , filter : Optional[Dict[ str , Any]] = None , ** kwargs ) -> List[Document]
Parameters Parameter Type Description embeddingUnion[List[float], np.ndarray]Embedding vector to search with kintNumber of documents to return (default: 4) filterOptional[Dict[str, Any]](Optional) Metadata filters to apply**kwargsAnyAdditional keyword arguments (currently unused)
Returns List[Document]: List of most similar Document objectsExample Usage # Get embedding for a query query_embedding = store.get_embeddings( "data science concepts" ) # Search using the embedding results = store.similarity_search_by_vector(query_embedding, k = 5 ) # Search with custom embedding custom_embedding = np.random.rand( 384 ) # Example 384-dim embedding results = store.similarity_search_by_vector(custom_embedding, k = 3 )
similarity_search_by_vector( embedding: Union[List[ float ], np.ndarray], k: Optional[ int ] = None , filter : Optional[Dict[ str , Any]] = None , ** kwargs ) -> List[Document]
Parameters Parameter Type Description embeddingUnion[List[float], np.ndarray]Embedding vector to search with kOptional[int](Optional) Number of documents to return (default: None, uses server default)filterOptional[Dict[str, Any]](Optional) Metadata filters to apply**kwargsAnyAdditional keyword arguments
Returns List[Document]: List of most similar Document objectsExample Usage query_embedding = store.get_embeddings( "data science concepts" ) results = store.similarity_search_by_vector(query_embedding, k = 5 )
similaritySearchVectorWithScore ( query : number [], k : number , filter ?: Record < string , any > ): Promise < [ Document , number ][] >
Parameters Parameter Type Description querynumber[]Embedding vector to search with knumberNumber of documents to return filterRecord<string, any>(Optional) Metadata filters to apply
Returns Promise<[Document, number][]>: Array of [Document, score] tuplesThe JS/TS method name is similaritySearchVectorWithScore (not similaritySearchByVector), and it returns score tuples unlike the Python SDKs which return documents only.
Example Usage const queryEmbedding = [ 0.1 , 0.2 , 0.3 , /* ... */ ]; const results = await store . similaritySearchVectorWithScore ( queryEmbedding , 5 ); for ( const [ doc , score ] of results ) { console . log ( `Score: ${ score . toFixed ( 4 ) } - ${ doc . pageContent . slice ( 0 , 100 ) } ...` ); }
Async
The Embedded and Python SDK provide async versions of this method prefixed with a: # asimilarity_search_by_vector — async variant docs = await store.asimilarity_search_by_vector(embedding, k = 5 )
JS/TS methods are natively async — all signatures above already return Promise<...>. No separate async variant is needed.
