DashVectorStore

class llama_index.vector_stores.DashVectorStore(collection: Optional[Any] = None, support_sparse_vector: bool = False, encoder: Optional[Any] = None)

Bases: VectorStore

Dash Vector Store.

In this vector store, embeddings and docs are stored within a DashVector collection.

During query time, the index uses DashVector to query for the top k most similar nodes.

Parameters

• collection (Optional[dashvector.Collection]) – DashVector collection instance

• support_sparse_vector (bool) – whether support sparse vector for collection.

• encoder (Optional[dashtext.SparseVectorEncoder]) – encoder for generating sparse vector from document

Attributes Summary

flat_metadata
stores_text

Methods Summary

add(nodes, **add_kwargs)	Add nodes to vector store.
delete(ref_doc_id, **delete_kwargs)	Delete nodes using with ref_doc_id.
query(query, **kwargs)	Query vector store.

Attributes Documentation

flat_metadata: bool = True

stores_text: bool = True

Methods Documentation

add(nodes: List[BaseNode], **add_kwargs: Any) → List[str]

Add nodes to vector store.

Parameters

nodes (List[BaseNode]) – list of nodes with embeddings

delete(ref_doc_id: str, **delete_kwargs: Any) → None

Delete nodes using with ref_doc_id.

Parameters

ref_doc_id (str) – The doc_id of the document to delete.

query(query: VectorStoreQuery, **kwargs: Any) → VectorStoreQueryResult

Query vector store.