Creates a MongoDB Atlas vectorSearch index for the VectorStore
Note**: This method may fail as it requires a MongoDB Atlas with these
pre-requisites <https://www.mongodb.com/docs/atlas/atlas-vector-search/create-index/#prerequisites>.
Currently, vector and full-text search index operations need to be
performed manually on the Atlas UI for shared M0 clusters.
create_vector_search_index(
self,
dimensions: int = 1,
filters: Optional[List[str]] = None,
update: bool = False,
wait_until_complete: Optional[float] = None,
vector_index_options: dict | None = None,
**kwargs: Any = {}
) -> None| Name | Type | Description |
|---|---|---|
dimensions | Optional[int] | Default: -1Number of dimensions in embedding. Should be |
filters | Optional[List[Dict[str, str]]] | Default: Noneadditional filters |
update | Optional[bool] | Default: FalseUpdates existing vectorSearch index. Defaults to False. |
wait_until_complete | Optional[float] | Default: NoneIf given, a TimeoutError is raised if search index is not ready after this number of seconds. If not given, the default, operation will not wait. |
kwargs | Any | Default: {}(Optional): Keyword arguments supplying any additional options to SearchIndexModel. |