Get the embeddings for the documents and add them to the vectorstore.
Documents are sent to the embeddings object
in batches of size embedding_chunk_size.
The embeddings are then upserted into the vectorstore
in batches of size batch_size.
aadd_documents(
self,
documents: Iterable[Document],
ids: Optional[List[str]] = None,
batch_size: int = 32,
embedding_chunk_size: int = 1000,
*,
namespace: Optional[str] = None,
**kwargs: Any = {}
) -> List[str]| Name | Type | Description |
|---|---|---|
documents* | Iterable[Document] | Iterable of Documents to add to the vectorstore. |
batch_size | int | Default: 32Batch size to use when upserting the embeddings. |
embedding_batch_size* | unknown | Chunk size to use when embedding the texts. |
namespace | Optional[str] | Default: NoneNamespace to use from the index. |