Get instance of an existing Neo4j vector index. This method will
return the instance of the store without inserting any new
embeddings.
Neo4j credentials are required in the form of url, username,
and password and optional database parameters along with
the index_name definition.
from_existing_index(
cls: Type[Neo4jVector],
embedding: Embeddings,
index_name: str,
search_type: SearchType = DEFAULT_SEARCH_TYPE,
keyword_index_name: Optional[str] = None,
embedding_dimension: Optional[int] = None,
text_node_properties: Optional[List[str]] = None,
retrieval_query: str = '',
**kwargs: Any = {}
) -> Neo4jVector| Name | Type | Description |
|---|---|---|
embedding* | Embeddings | Embeddings object to use for embedding generation. |
index_name* | str | Name of the existing vector index. |
search_type | SearchType | Default: DEFAULT_SEARCH_TYPEType of search to perform (default: VECTOR). |
keyword_index_name | Optional[str] | Default: NoneName of the keyword index for hybrid search. |
embedding_dimension | Optional[int] | Default: NoneDimension of the embeddings. |
text_node_properties | Optional[List[str]] | Default: NoneOptional list of node properties to use as text
content. When provided, the retrieval query will concatenate these
properties. If not provided, uses the single |
retrieval_query | str | Default: ''Optional custom retrieval query. If provided, takes precedence over auto-generated queries. |
**kwargs | Any | Default: {}Additional arguments passed to the Neo4jVector constructor. |