Parameter | Type | Description |
---|---|---|
vectors | List[Dict[str, Union[int, List[float], bytes, Dict[str, Union[str, int, bool, float]]]]] | A list of dictionaries, where each dictionary has the format {"id": int, "vector": List[float], "item": bytes} . |
vector
dictionary has the following fields:
id
(int
): Unique integer identifier for the vector.vector
(List[float]
): Embedding vector as a list of floats.item
(bytes
): Item contents in bytes (optional)ValueError
RuntimeError
id
and vector
fields as tuples, if you wish to skip the dictionary. On big datasets, this can make a signficant difference in memory usage.Upsert
Secondary Overload: NumPy Array FormatParameter | Type | Description |
---|---|---|
ids | np.ndarray | 1D NumPy array of shape (num_items,) with dtype=int , containing unique integer identifiers for each vector. Length must match vectors . |
vectors | np.ndarray | 2D NumPy array of shape (num_items, vector_dim) with dtype=float , representing vector embeddings. |
ValueError
RuntimeError