add
Function
Adds a document index to a vector database. Specifically, this API first embeds a document chunk to obtain vectors, and then stores the vectors into a vector database.
Prototype
def add(ids: List[int], embeddings: np.ndarray, document_id)
Parameters
Parameter |
Data Type |
Required/Optional |
Description |
|---|---|---|---|
ids |
List[int] |
Required |
Index ID list of vectors to be added. Its length range is [0, 10 million). |
embeddings |
ndarray |
Required |
NumPy array object. |
document_id |
Integer |
Optional |
ID of the document to which vectors to be added belong. |
The shape of embeddings must be 2D. The number of vectors contained in embeddings must be equal to the length of ids. The total number of added vectors at a time must be less than 10 million.
Parent topic: OpenGaussDB