FalkorDBVector

Returns the Embeddings model being used by the Vectorstore

Check if the vector index exists in the FalkorDB database and returns its embedding dimension, entity_type, entity_label, entity_property

This method;

1. queries the FalkorDB database for existing indexes
2. attempts to retrieve the dimension of the vector index with the specified node label & index type
3. If the index exists, its dimension is returned.
4. Else if the index doesn't exist, None is returned.

Check if the vector index exists in the FalkorDB database and returns its embedding dimension, entity_type, entity_label, entity_property

This method;

1. queries the FalkorDB database for existing indexes
2. attempts to retrieve the dimension of the vector index with the specified label & index type
3. If the index exists, its dimension is returned.
4. Else if the index doesn't exist, None is returned.

Check if the fulltext index exists in the FalkorDB database

This method queries the FalkorDB database for existing fts indexes with the specified name.

This method creates a new vector index on a node in FalkorDB.

This method creates an new vector index on a relationship/edge in FalkorDB.

This method constructs a Cypher query and executes it to create a new full text index in FalkorDB Args: text_node_properties (List[str]): List of node properties to be indexed.If not provided, defaults to self.text_node_property.

Add embeddings to the vectorstore.

Run more texts through the embeddings and add to the vectorstore.

This function takes List[Document] element(s) and populates the existing store with a default node or default node(s) that represent the element(s) and returns the id(s) of the newly created node(s).

Return FalkorDBVector initialized from texts and embeddings.

Get instance of an existing FalkorDB vector index. This method will return the instance of the store without inserting any new embeddings.

Get instance of an existing FalkorDB relationship vector index. This method will return the instance of the store without inserting any new embeddings.

Initialize and return a FalkorDBVector instance from an existing graph using the database name

This method initializes a FalkorDBVector instance using the provided parameters and the existing graph. It validates the existence of the indices and creates new ones if they don't exist.

Return FalkorDBVector initialized from documents and embeddings.

Construct FalkorDBVector wrapper from raw documents and pre- generated embeddings.

Return FalkorDBVector initialized from documents and embeddings.

Example: .. code-block:: python

from langchain_community.vectorstores.falkordb_vector import ( FalkorDBVector ) from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() text_embeddings = embeddings.embed_documents(texts) text_embedding_pairs = list(zip(texts, text_embeddings)) vectorstore = FalkorDBVector.from_embeddings( text_embedding_pairs, embeddings )

Run similarity search with FalkorDBVector.

Return docs most similar to embedding vector.

Perform a similarity search in the FalkorDB database using a given vector and return the top k similar documents with their scores.

This method uses a Cypher query to find the top k documents that are most similar to a given embedding. The similarity is measured using a vector index in the FalkorDB database. The results are returned as a list of tuples, each containing a Document object and its similarity score.

Return docs most similar to query.

Return docs selected using the maximal marginal relevance.

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

This function updates an existing document in the store based on the document_id.

This function deletes an item from the store based on the item_id. Args: ids: A list of IDs of the documents to be deleted. If None, deletes all documents. Returns: Optional[bool]: True if documents were deleted, False otherwise.