TimescaleVectorStore#

class llama_index.vector_stores.TimescaleVectorStore(service_url: str, table_name: str, num_dimensions: int = 1536, time_partition_interval: Optional[timedelta] = None)#

Bases: VectorStore

Attributes Summary

`DEFAULT_INDEX_TYPE`
`flat_metadata`
`stores_text`

Methods Summary

`add`(nodes, **add_kwargs)	Add nodes with embedding to vector store.
`aquery`(query, **kwargs)	Asynchronously query vector store.
`async_add`(nodes, **add_kwargs)	Asynchronously add nodes with embedding to vector store.
`close`()
`create_index`([index_type])
`date_to_range_filter`(**kwargs)
`delete`(ref_doc_id, **delete_kwargs)	Delete nodes using with ref_doc_id.
`drop_index`()
`from_params`(service_url, table_name[, ...])
`query`(query, **kwargs)	Query vector store.

Attributes Documentation

DEFAULT_INDEX_TYPE = 1#

flat_metadata = False#

stores_text: bool = True#

Methods Documentation

add(nodes: List[BaseNode], **add_kwargs: Any) → List[str]#: Add nodes with embedding to vector store.

async aquery(query: VectorStoreQuery, **kwargs: Any) → VectorStoreQueryResult#: Asynchronously query vector store. NOTE: this is not implemented for all vector stores. If not implemented, it will just call query synchronously.

async async_add(nodes: List[BaseNode], **add_kwargs: Any) → List[str]#: Asynchronously add nodes with embedding to vector store. NOTE: this is not implemented for all vector stores. If not implemented, it will just call add synchronously.

async close() → None#

create_index(index_type: IndexType = IndexType.TIMESCALE_VECTOR, **kwargs: Any) → None#

date_to_range_filter(**kwargs: Any) → Any#

delete(ref_doc_id: str, **delete_kwargs: Any) → None#: Delete nodes using with ref_doc_id.

drop_index() → None#

classmethod from_params(service_url: str, table_name: str, num_dimensions: int = 1536, time_partition_interval: Optional[timedelta] = None) → TimescaleVectorStore#

query(query: VectorStoreQuery, **kwargs: Any) → VectorStoreQueryResult#: Query vector store.